forked from manbo/internal-docs
Compare commits
13 Commits
master
...
dc5db4f3ec
| Author | SHA1 | Date | |
|---|---|---|---|
|
dc5db4f3ec | ||
|
|
87ba7a5516 | ||
|
|
6ae0f24af3 | ||
|
|
c95fca657b | ||
|
|
704277f011 | ||
| 25bc355717 | |||
|
|
89997f1125 | ||
|
|
4ec1b0b7a8 | ||
|
|
327fc36bf7 | ||
|
|
72b653f35d | ||
| 0e0f951e12 | |||
| ace1130179 | |||
| 0613edcf61 |
7
.gitignore
vendored
Normal file
7
.gitignore
vendored
Normal file
@@ -0,0 +1,7 @@
|
||||
papers/Topic8 Network Traffic Generation/NetDiffusion Network Data Augmentation Through Protocol-Constrained Traffic Generation/NetDiffusion Network Data Augmentation Through Protocol-Constrained Traffic Gener_1_33_translate_20260130214700.pdf
|
||||
arxiv-style/*.pdf
|
||||
arxiv-style/*.aux
|
||||
arxiv-style/*.log
|
||||
arxiv-style/*.blg
|
||||
arxiv-style/*.bbl
|
||||
arxiv-style/*.out
|
||||
262
arxiv-style/arxiv.sty
Normal file
262
arxiv-style/arxiv.sty
Normal file
@@ -0,0 +1,262 @@
|
||||
\NeedsTeXFormat{LaTeX2e}
|
||||
|
||||
\ProcessOptions\relax
|
||||
|
||||
% fonts
|
||||
\renewcommand{\rmdefault}{ptm}
|
||||
\renewcommand{\sfdefault}{phv}
|
||||
|
||||
% set page geometry
|
||||
\usepackage[verbose=true,letterpaper]{geometry}
|
||||
\AtBeginDocument{
|
||||
\newgeometry{
|
||||
textheight=9in,
|
||||
textwidth=6.5in,
|
||||
top=1in,
|
||||
headheight=14pt,
|
||||
headsep=25pt,
|
||||
footskip=30pt
|
||||
}
|
||||
}
|
||||
|
||||
\widowpenalty=10000
|
||||
\clubpenalty=10000
|
||||
\flushbottom
|
||||
\sloppy
|
||||
|
||||
|
||||
|
||||
\newcommand{\headeright}{A Preprint}
|
||||
\newcommand{\undertitle}{A Preprint}
|
||||
\newcommand{\shorttitle}{\@title}
|
||||
|
||||
\usepackage{fancyhdr}
|
||||
\fancyhf{}
|
||||
\pagestyle{fancy}
|
||||
\renewcommand{\headrulewidth}{0.4pt}
|
||||
\fancyheadoffset{0pt}
|
||||
\rhead{\scshape \footnotesize \headeright}
|
||||
\chead{\shorttitle}
|
||||
\cfoot{\thepage}
|
||||
|
||||
|
||||
%Handling Keywords
|
||||
\def\keywordname{{\bfseries \emph{Keywords}}}%
|
||||
\def\keywords#1{\par\addvspace\medskipamount{\rightskip=0pt plus1cm
|
||||
\def\and{\ifhmode\unskip\nobreak\fi\ $\cdot$
|
||||
}\noindent\keywordname\enspace\ignorespaces#1\par}}
|
||||
|
||||
% font sizes with reduced leading
|
||||
\renewcommand{\normalsize}{%
|
||||
\@setfontsize\normalsize\@xpt\@xipt
|
||||
\abovedisplayskip 7\p@ \@plus 2\p@ \@minus 5\p@
|
||||
\abovedisplayshortskip \z@ \@plus 3\p@
|
||||
\belowdisplayskip \abovedisplayskip
|
||||
\belowdisplayshortskip 4\p@ \@plus 3\p@ \@minus 3\p@
|
||||
}
|
||||
\normalsize
|
||||
\renewcommand{\small}{%
|
||||
\@setfontsize\small\@ixpt\@xpt
|
||||
\abovedisplayskip 6\p@ \@plus 1.5\p@ \@minus 4\p@
|
||||
\abovedisplayshortskip \z@ \@plus 2\p@
|
||||
\belowdisplayskip \abovedisplayskip
|
||||
\belowdisplayshortskip 3\p@ \@plus 2\p@ \@minus 2\p@
|
||||
}
|
||||
\renewcommand{\footnotesize}{\@setfontsize\footnotesize\@ixpt\@xpt}
|
||||
\renewcommand{\scriptsize}{\@setfontsize\scriptsize\@viipt\@viiipt}
|
||||
\renewcommand{\tiny}{\@setfontsize\tiny\@vipt\@viipt}
|
||||
\renewcommand{\large}{\@setfontsize\large\@xiipt{14}}
|
||||
\renewcommand{\Large}{\@setfontsize\Large\@xivpt{16}}
|
||||
\renewcommand{\LARGE}{\@setfontsize\LARGE\@xviipt{20}}
|
||||
\renewcommand{\huge}{\@setfontsize\huge\@xxpt{23}}
|
||||
\renewcommand{\Huge}{\@setfontsize\Huge\@xxvpt{28}}
|
||||
|
||||
% sections with less space
|
||||
\providecommand{\section}{}
|
||||
\renewcommand{\section}{%
|
||||
\@startsection{section}{1}{\z@}%
|
||||
{-2.0ex \@plus -0.5ex \@minus -0.2ex}%
|
||||
{ 1.5ex \@plus 0.3ex \@minus 0.2ex}%
|
||||
{\large\bf\raggedright}%
|
||||
}
|
||||
\providecommand{\subsection}{}
|
||||
\renewcommand{\subsection}{%
|
||||
\@startsection{subsection}{2}{\z@}%
|
||||
{-1.8ex \@plus -0.5ex \@minus -0.2ex}%
|
||||
{ 0.8ex \@plus 0.2ex}%
|
||||
{\normalsize\bf\raggedright}%
|
||||
}
|
||||
\providecommand{\subsubsection}{}
|
||||
\renewcommand{\subsubsection}{%
|
||||
\@startsection{subsubsection}{3}{\z@}%
|
||||
{-1.5ex \@plus -0.5ex \@minus -0.2ex}%
|
||||
{ 0.5ex \@plus 0.2ex}%
|
||||
{\normalsize\bf\raggedright}%
|
||||
}
|
||||
\providecommand{\paragraph}{}
|
||||
\renewcommand{\paragraph}{%
|
||||
\@startsection{paragraph}{4}{\z@}%
|
||||
{1.5ex \@plus 0.5ex \@minus 0.2ex}%
|
||||
{-1em}%
|
||||
{\normalsize\bf}%
|
||||
}
|
||||
\providecommand{\subparagraph}{}
|
||||
\renewcommand{\subparagraph}{%
|
||||
\@startsection{subparagraph}{5}{\z@}%
|
||||
{1.5ex \@plus 0.5ex \@minus 0.2ex}%
|
||||
{-1em}%
|
||||
{\normalsize\bf}%
|
||||
}
|
||||
\providecommand{\subsubsubsection}{}
|
||||
\renewcommand{\subsubsubsection}{%
|
||||
\vskip5pt{\noindent\normalsize\rm\raggedright}%
|
||||
}
|
||||
|
||||
% float placement
|
||||
\renewcommand{\topfraction }{0.85}
|
||||
\renewcommand{\bottomfraction }{0.4}
|
||||
\renewcommand{\textfraction }{0.1}
|
||||
\renewcommand{\floatpagefraction}{0.7}
|
||||
|
||||
\newlength{\@abovecaptionskip}\setlength{\@abovecaptionskip}{7\p@}
|
||||
\newlength{\@belowcaptionskip}\setlength{\@belowcaptionskip}{\z@}
|
||||
|
||||
\setlength{\abovecaptionskip}{\@abovecaptionskip}
|
||||
\setlength{\belowcaptionskip}{\@belowcaptionskip}
|
||||
|
||||
% swap above/belowcaptionskip lengths for tables
|
||||
\renewenvironment{table}
|
||||
{\setlength{\abovecaptionskip}{\@belowcaptionskip}%
|
||||
\setlength{\belowcaptionskip}{\@abovecaptionskip}%
|
||||
\@float{table}}
|
||||
{\end@float}
|
||||
|
||||
% footnote formatting
|
||||
\setlength{\footnotesep }{6.65\p@}
|
||||
\setlength{\skip\footins}{9\p@ \@plus 4\p@ \@minus 2\p@}
|
||||
\renewcommand{\footnoterule}{\kern-3\p@ \hrule width 12pc \kern 2.6\p@}
|
||||
\setcounter{footnote}{0}
|
||||
|
||||
% paragraph formatting
|
||||
\setlength{\parindent}{\z@}
|
||||
\setlength{\parskip }{5.5\p@}
|
||||
|
||||
% list formatting
|
||||
\setlength{\topsep }{4\p@ \@plus 1\p@ \@minus 2\p@}
|
||||
\setlength{\partopsep }{1\p@ \@plus 0.5\p@ \@minus 0.5\p@}
|
||||
\setlength{\itemsep }{2\p@ \@plus 1\p@ \@minus 0.5\p@}
|
||||
\setlength{\parsep }{2\p@ \@plus 1\p@ \@minus 0.5\p@}
|
||||
\setlength{\leftmargin }{3pc}
|
||||
\setlength{\leftmargini }{\leftmargin}
|
||||
\setlength{\leftmarginii }{2em}
|
||||
\setlength{\leftmarginiii}{1.5em}
|
||||
\setlength{\leftmarginiv }{1.0em}
|
||||
\setlength{\leftmarginv }{0.5em}
|
||||
\def\@listi {\leftmargin\leftmargini}
|
||||
\def\@listii {\leftmargin\leftmarginii
|
||||
\labelwidth\leftmarginii
|
||||
\advance\labelwidth-\labelsep
|
||||
\topsep 2\p@ \@plus 1\p@ \@minus 0.5\p@
|
||||
\parsep 1\p@ \@plus 0.5\p@ \@minus 0.5\p@
|
||||
\itemsep \parsep}
|
||||
\def\@listiii{\leftmargin\leftmarginiii
|
||||
\labelwidth\leftmarginiii
|
||||
\advance\labelwidth-\labelsep
|
||||
\topsep 1\p@ \@plus 0.5\p@ \@minus 0.5\p@
|
||||
\parsep \z@
|
||||
\partopsep 0.5\p@ \@plus 0\p@ \@minus 0.5\p@
|
||||
\itemsep \topsep}
|
||||
\def\@listiv {\leftmargin\leftmarginiv
|
||||
\labelwidth\leftmarginiv
|
||||
\advance\labelwidth-\labelsep}
|
||||
\def\@listv {\leftmargin\leftmarginv
|
||||
\labelwidth\leftmarginv
|
||||
\advance\labelwidth-\labelsep}
|
||||
\def\@listvi {\leftmargin\leftmarginvi
|
||||
\labelwidth\leftmarginvi
|
||||
\advance\labelwidth-\labelsep}
|
||||
|
||||
% create title
|
||||
\providecommand{\maketitle}{}
|
||||
\renewcommand{\maketitle}{%
|
||||
\par
|
||||
\begingroup
|
||||
\renewcommand{\thefootnote}{\fnsymbol{footnote}}
|
||||
% for perfect author name centering
|
||||
%\renewcommand{\@makefnmark}{\hbox to \z@{$^{\@thefnmark}$\hss}}
|
||||
% The footnote-mark was overlapping the footnote-text,
|
||||
% added the following to fix this problem (MK)
|
||||
\long\def\@makefntext##1{%
|
||||
\parindent 1em\noindent
|
||||
\hbox to 1.8em{\hss $\m@th ^{\@thefnmark}$}##1
|
||||
}
|
||||
\thispagestyle{empty}
|
||||
\@maketitle
|
||||
\@thanks
|
||||
%\@notice
|
||||
\endgroup
|
||||
\let\maketitle\relax
|
||||
\let\thanks\relax
|
||||
}
|
||||
|
||||
% rules for title box at top of first page
|
||||
\newcommand{\@toptitlebar}{
|
||||
\hrule height 2\p@
|
||||
\vskip 0.25in
|
||||
\vskip -\parskip%
|
||||
}
|
||||
\newcommand{\@bottomtitlebar}{
|
||||
\vskip 0.29in
|
||||
\vskip -\parskip
|
||||
\hrule height 2\p@
|
||||
\vskip 0.09in%
|
||||
}
|
||||
|
||||
% create title (includes both anonymized and non-anonymized versions)
|
||||
\providecommand{\@maketitle}{}
|
||||
\renewcommand{\@maketitle}{%
|
||||
\vbox{%
|
||||
\hsize\textwidth
|
||||
\linewidth\hsize
|
||||
\vskip 0.1in
|
||||
\@toptitlebar
|
||||
\centering
|
||||
{\LARGE\sc \@title\par}
|
||||
\@bottomtitlebar
|
||||
\textsc{\undertitle}\\
|
||||
\vskip 0.1in
|
||||
\def\And{%
|
||||
\end{tabular}\hfil\linebreak[0]\hfil%
|
||||
\begin{tabular}[t]{c}\bf\rule{\z@}{24\p@}\ignorespaces%
|
||||
}
|
||||
\def\AND{%
|
||||
\end{tabular}\hfil\linebreak[4]\hfil%
|
||||
\begin{tabular}[t]{c}\bf\rule{\z@}{24\p@}\ignorespaces%
|
||||
}
|
||||
\begin{tabular}[t]{c}\bf\rule{\z@}{24\p@}\@author\end{tabular}%
|
||||
\vskip 0.4in \@minus 0.1in \center{\@date} \vskip 0.2in
|
||||
}
|
||||
}
|
||||
|
||||
% add conference notice to bottom of first page
|
||||
\newcommand{\ftype@noticebox}{8}
|
||||
\newcommand{\@notice}{%
|
||||
% give a bit of extra room back to authors on first page
|
||||
\enlargethispage{2\baselineskip}%
|
||||
\@float{noticebox}[b]%
|
||||
\footnotesize\@noticestring%
|
||||
\end@float%
|
||||
}
|
||||
|
||||
% abstract styling
|
||||
\renewenvironment{abstract}
|
||||
{
|
||||
\centerline
|
||||
{\large \bfseries \scshape Abstract}
|
||||
\begin{quote}
|
||||
}
|
||||
{
|
||||
\end{quote}
|
||||
}
|
||||
|
||||
\endinput
|
||||
95
arxiv-style/equations.tex
Normal file
95
arxiv-style/equations.tex
Normal file
@@ -0,0 +1,95 @@
|
||||
\documentclass[10pt, twocolumn]{article}
|
||||
\usepackage{amsmath, amssymb}
|
||||
\usepackage{bm}
|
||||
\usepackage[margin=1in]{geometry}
|
||||
\usepackage{microtype}
|
||||
|
||||
\title{Equations: Mask-DDPM Methodology}
|
||||
\author{}
|
||||
\date{}
|
||||
|
||||
\begin{document}
|
||||
\maketitle
|
||||
|
||||
\section{Problem Formulation}
|
||||
Each training instance is a fixed-length window of length $L$, comprising continuous channels $\bm{X} \in \mathbb{R}^{L \times d_c}$ and discrete channels $\bm{Y} = \{y^{(j)}_{1:L}\}_{j=1}^{d_d}$, where each discrete variable satisfies $y^{(j)}_t \in \mathcal{V}_j$ for a finite vocabulary $\mathcal{V}_j$.
|
||||
|
||||
\section{Transformer Trend Module for Continuous Dynamics}
|
||||
We posit an additive decomposition of the continuous signal:
|
||||
\begin{equation}
|
||||
\bm{X} = \bm{S} + \bm{R},
|
||||
\label{eq:additive_decomp}
|
||||
\end{equation}
|
||||
where $\bm{S} \in \mathbb{R}^{L \times d_c}$ captures the smooth temporal trend and $\bm{R} \in \mathbb{R}^{L \times d_c}$ represents distributional residuals.
|
||||
|
||||
The causal Transformer trend extractor $f_{\phi}$ predicts the next-step trend via:
|
||||
\begin{equation}
|
||||
\hat{\bm{S}}_{t+1} = f_{\phi}(\bm{X}_{1:t}), \quad t = 1, \dots, L-1.
|
||||
\label{eq:trend_prediction}
|
||||
\end{equation}
|
||||
Training minimizes the mean-squared error:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{trend}}(\phi) = \frac{1}{(L-1)d_c} \sum_{t=1}^{L-1} \bigl\| \hat{\bm{S}}_{t+1} - \bm{X}_{t+1} \bigr\|_2^2.
|
||||
\label{eq:trend_loss}
|
||||
\end{equation}
|
||||
At inference, the residual target is defined as $\bm{R} = \bm{X} - \hat{\bm{S}}$.
|
||||
|
||||
\section{DDPM for Continuous Residual Generation}
|
||||
Let $K$ denote diffusion steps with noise schedule $\{\beta_k\}_{k=1}^K$, $\alpha_k = 1 - \beta_k$, and $\bar{\alpha}_k = \prod_{i=1}^k \alpha_i$. The forward corruption process is:
|
||||
\begin{align}
|
||||
q(\bm{r}_k \mid \bm{r}_0) &= \mathcal{N}\bigl( \sqrt{\bar{\alpha}_k}\,\bm{r}_0,\; (1 - \bar{\alpha}_k)\mathbf{I} \bigr), \\
|
||||
\bm{r}_k &= \sqrt{\bar{\alpha}_k}\,\bm{r}_0 + \sqrt{1 - \bar{\alpha}_k}\,\boldsymbol{\epsilon}, \quad \boldsymbol{\epsilon} \sim \mathcal{N}(\mathbf{0}, \mathbf{I}),
|
||||
\label{eq:forward_process}
|
||||
\end{align}
|
||||
where $\bm{r}_0 \equiv \bm{R}$.
|
||||
|
||||
The reverse process is parameterized as:
|
||||
\begin{equation}
|
||||
p_{\theta}(\bm{r}_{k-1} \mid \bm{r}_k, \hat{\bm{S}}) = \mathcal{N}\bigl( \boldsymbol{\mu}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}),\; \boldsymbol{\Sigma}(k) \bigr).
|
||||
\label{eq:reverse_process}
|
||||
\end{equation}
|
||||
Training employs the $\epsilon$-prediction objective:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{cont}}(\theta) = \mathbb{E}_{k,\bm{r}_0,\boldsymbol{\epsilon}} \left[ \bigl\| \boldsymbol{\epsilon} - \boldsymbol{\epsilon}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}) \bigr\|_2^2 \right].
|
||||
\label{eq:ddpm_loss}
|
||||
\end{equation}
|
||||
Optionally, SNR-based reweighting yields:
|
||||
\begin{equation}
|
||||
\mathcal{L}^{\text{snr}}_{\text{cont}}(\theta) = \mathbb{E}_{k,\bm{r}_0,\boldsymbol{\epsilon}} \left[ w_k \bigl\| \boldsymbol{\epsilon} - \boldsymbol{\epsilon}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}) \bigr\|_2^2 \right],
|
||||
\label{eq:snr_loss}
|
||||
\end{equation}
|
||||
where $w_k = \min(\mathrm{SNR}_k, \gamma) / \mathrm{SNR}_k$ and $\mathrm{SNR}_k = \bar{\alpha}_k / (1 - \bar{\alpha}_k)$. The final continuous output is reconstructed as $\hat{\bm{X}} = \hat{\bm{S}} + \hat{\bm{R}}$.
|
||||
|
||||
\section{Masked Diffusion for Discrete Variables}
|
||||
For discrete channel $j$, the forward masking process follows schedule $\{m_k\}_{k=1}^K$:
|
||||
\begin{equation}
|
||||
q(y^{(j)}_k \mid y^{(j)}_0) =
|
||||
\begin{cases}
|
||||
y^{(j)}_0, & \text{with probability } 1 - m_k, \\
|
||||
\texttt{[MASK]}, & \text{with probability } m_k,
|
||||
\end{cases}
|
||||
\label{eq:masking_process}
|
||||
\end{equation}
|
||||
applied independently across variables and timesteps.
|
||||
|
||||
The denoiser $h_{\psi}$ predicts categorical distributions conditioned on continuous context:
|
||||
\begin{equation}
|
||||
p_{\psi}\bigl( y^{(j)}_0 \mid y_k, k, \hat{\bm{S}}, \hat{\bm{X}} \bigr) = h_{\psi}(y_k, k, \hat{\bm{S}}, \hat{\bm{X}}).
|
||||
\label{eq:discrete_denoising}
|
||||
\end{equation}
|
||||
Training minimizes the categorical cross-entropy:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{disc}}(\psi) = \mathbb{E}_{k} \left[ \frac{1}{|\mathcal{M}|} \sum_{(j,t) \in \mathcal{M}} \mathrm{CE}\bigl( h_{\psi}(y_k, k, \hat{\bm{S}}, \hat{\bm{X}})_{j,t},\; y^{(j)}_{0,t} \bigr) \right],
|
||||
\label{eq:discrete_loss}
|
||||
\end{equation}
|
||||
where $\mathcal{M}$ denotes masked positions at step $k$.
|
||||
|
||||
\section{Joint Optimization}
|
||||
The combined objective balances continuous and discrete learning:
|
||||
\begin{equation}
|
||||
\mathcal{L} = \lambda \, \mathcal{L}_{\text{cont}} + (1 - \lambda) \, \mathcal{L}_{\text{disc}}, \quad \lambda \in [0,1].
|
||||
\label{eq:joint_objective}
|
||||
\end{equation}
|
||||
Type-aware routing enforces deterministic reconstruction $\hat{x}^{(i)} = g_i(\hat{\bm{X}}, \hat{\bm{Y}})$ for derived variables.
|
||||
|
||||
\end{document}
|
||||
BIN
arxiv-style/fig-design-v1.png
Normal file
BIN
arxiv-style/fig-design-v1.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 582 KiB |
BIN
arxiv-style/fig-design-v2.png
Normal file
BIN
arxiv-style/fig-design-v2.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 669 KiB |
256
arxiv-style/main.tex
Normal file
256
arxiv-style/main.tex
Normal file
@@ -0,0 +1,256 @@
|
||||
\documentclass{article}
|
||||
|
||||
\usepackage{arxiv}
|
||||
|
||||
\usepackage[utf8]{inputenc} % allow utf-8 input
|
||||
\usepackage[T1]{fontenc} % use 8-bit T1 fonts
|
||||
\usepackage{hyperref} % hyperlinks
|
||||
\usepackage{url} % simple URL typesetting
|
||||
\usepackage{booktabs} % professional-quality tables
|
||||
\usepackage{amsfonts} % blackboard math symbols
|
||||
\usepackage{nicefrac} % compact symbols for 1/2, etc.
|
||||
\usepackage{microtype} % microtypography
|
||||
\usepackage{amsmath} % cleveref must be loaded after amsmath!
|
||||
\usepackage{cleveref} % smart cross-referencing
|
||||
\usepackage{lipsum} % Can be removed after putting your text content
|
||||
\usepackage{graphicx}
|
||||
\usepackage{natbib}
|
||||
\usepackage{doi}
|
||||
|
||||
% Packages for equations
|
||||
\usepackage{amssymb}
|
||||
\usepackage{bm}
|
||||
|
||||
% 标题
|
||||
\title{Your Paper Title: A Deep Learning Approach for Something}
|
||||
|
||||
% 若不需要日期，取消下面一行的注释
|
||||
%\date{}
|
||||
|
||||
\newif\ifuniqueAffiliation
|
||||
\uniqueAffiliationtrue
|
||||
|
||||
\ifuniqueAffiliation % 标准作者块
|
||||
\author{
|
||||
David S.~Hippocampus \\
|
||||
Department of Computer Science\\
|
||||
Cranberry-Lemon University\\
|
||||
Pittsburgh, PA 15213 \\
|
||||
\texttt{hippo@cs.cranberry-lemon.edu} \\
|
||||
\And
|
||||
Elias D.~Striatum \\
|
||||
Department of Electrical Engineering\\
|
||||
Mount-Sheikh University\\
|
||||
Santa Narimana, Levand \\
|
||||
\texttt{stariate@ee.mount-sheikh.edu} \\
|
||||
\And
|
||||
John Q.~Doe \\
|
||||
Department of Mathematics\\
|
||||
University of California, Berkeley\\
|
||||
Berkeley, CA 94720 \\
|
||||
\texttt{johndoe@math.berkeley.edu}
|
||||
}
|
||||
\fi
|
||||
|
||||
% 页眉设置
|
||||
\renewcommand{\shorttitle}{\textit{arXiv} Template}
|
||||
|
||||
%%% PDF 元数据
|
||||
\hypersetup{
|
||||
pdftitle={Your Paper Title},
|
||||
pdfsubject={cs.LG, cs.CR},
|
||||
pdfauthor={David S.~Hippocampus, Elias D.~Striatum},
|
||||
pdfkeywords={Keyword1, Keyword2, Keyword3},
|
||||
}
|
||||
|
||||
\begin{document}
|
||||
\maketitle
|
||||
|
||||
\begin{abstract}
|
||||
Here is the abstract of your paper.
|
||||
\end{abstract}
|
||||
|
||||
% 关键词
|
||||
\keywords{Machine Learning \and Cyber Defense \and Benchmark \and Methodology}
|
||||
|
||||
% 1. Introduction
|
||||
\section{Introduction}
|
||||
\label{sec:intro}
|
||||
Here introduces the background, problem statement, and contribution.
|
||||
|
||||
% 2. Related Work
|
||||
\section{Related Work}
|
||||
\label{sec:related}
|
||||
Early generation of network data oriented towards ``realism'' mostly remained at the packet/flow header level, either through replay or statistical synthesis based on single-point observations. Swing, in a closed-loop, network-responsive manner, extracts user/application/network distributions from single-point observations to reproduce burstiness and correlation across multiple time scales \citep{10.1145/1151659.1159928,10.1145/1159913.1159928}. Subsequently, a series of works advanced header synthesis to learning-based generation: the WGAN-based method added explicit verification of protocol field consistency to NetFlow/IPFIX \citep{Ring_2019}, NetShare reconstructed header modeling as flow-level time series and improved fidelity and scalability through domain encoding and parallel fine-tuning \citep{10.1145/3544216.3544251}, and DoppelGANger preserved the long-range structure and downstream sorting consistency of networked time series by decoupling attributes from sequences \citep{Lin_2020}. However, in industrial control system (ICS) scenarios, the original PCAP is usually not shareable, and public testbeds (such as SWaT, WADI) mostly provide process/monitoring telemetry and protocol interactions for security assessment, but public datasets emphasize operational variables rather than packet-level traces \citep{7469060,10.1145/3055366.3055375}. This makes ``synthesis at the feature/telemetry level, aware of protocol and semantics'' more feasible and necessary in practice: we are more concerned with reproducing high-level distributions and multi-scale temporal patterns according to operational semantics and physical constraints without relying on the original packets. From this perspective, the generation paradigm naturally shifts from ``packet syntax reproduction'' to ``modeling of high-level spatio-temporal distributions and uncertainties'', requiring stable training, strong distribution fitting, and interpretable uncertainty characterization.
|
||||
|
||||
Diffusion models exhibit good fit along this path: DDPM achieves high-quality sampling and stable optimization through efficient $\epsilon$ parameterization and weighted variational objectives \citep{NEURIPS2020_4c5bcfec}, the SDE perspective unifies score-based and diffusion, providing likelihood evaluation and prediction-correction sampling strategies based on probability flow ODEs \citep{song2021scorebasedgenerativemodelingstochastic}. For time series, TimeGrad replaces the constrained output distribution with conditional denoising, capturing high-dimensional correlations at each step \citep{rasul2021autoregressivedenoisingdiffusionmodels}; CSDI explicitly performs conditional diffusion and uses two-dimensional attention to simultaneously leverage temporal and cross-feature dependencies, suitable for conditioning and filling in missing values \citep{tashiro2021csdiconditionalscorebaseddiffusion}; in a more general spatio-temporal structure, DiffSTG generalizes diffusion to spatio-temporal graphs, combining TCN/GCN with denoising U-Net to improve CRPS and inference efficiency in a non-autoregressive manner \citep{wen2024diffstgprobabilisticspatiotemporalgraph}, and PriSTI further enhances conditional features and geographical relationships, maintaining robustness under high missing rates and sensor failures \citep{liu2023pristiconditionaldiffusionframework}; in long sequences and continuous domains, DiffWave verifies that diffusion can also match the quality of strong vocoders under non-autoregressive fast synthesis \citep{kong2021diffwaveversatilediffusionmodel}; studies on cellular communication traffic show that diffusion can recover spatio-temporal patterns and provide uncertainty characterization at the urban scale \citep{11087622}. These results overall point to a conclusion: when the research focus is on ``telemetry/high-level features'' rather than raw messages, diffusion models provide stable and fine-grained distribution fitting and uncertainty quantification, which is exactly in line with the requirements of ICS telemetry synthesis. Meanwhile, directly entrusting all structures to a ``monolithic diffusion'' is not advisable: long-range temporal skeletons and fine-grained marginal distributions often have optimization tensions, requiring explicit decoupling in modeling.
|
||||
|
||||
Looking further into the mechanism complexity of ICS: its channel types are inherently mixed, containing both continuous process trajectories and discrete supervision/status variables, and discrete channels must be ``legal'' under operational constraints. The aforementioned progress in time series diffusion has mainly occurred in continuous spaces, but discrete diffusion has also developed systematic methods: D3PM improves sampling quality and likelihood through absorption/masking and structured transitions in discrete state spaces \citep{austin2023structureddenoisingdiffusionmodels}, subsequent masked diffusion provides stable reconstruction on categorical data in a more simplified form \citep{Lin_2020}, multinomial diffusion directly defines diffusion on a finite vocabulary through mechanisms such as argmax flows \citep{hoogeboom2021argmaxflowsmultinomialdiffusion}, and Diffusion-LM demonstrates an effective path for controllable text generation by imposing gradient constraints in continuous latent spaces \citep{li2022diffusionlmimprovescontrollabletext}. From the perspectives of protocols and finite-state machines, coverage-guided fuzz testing emphasizes the criticality of ``sequence legality and state coverage'' \citep{meng2025aflnetyearslatercoverageguided,godefroid2017learnfuzzmachinelearninginput,she2019neuzzefficientfuzzingneural}, echoing the concept of ``legality by construction'' in discrete diffusion: preferentially adopting absorption/masking diffusion on discrete channels, supplemented by type-aware conditioning and sampling constraints, to avoid semantic invalidity and marginal distortion caused by post hoc thresholding.
|
||||
|
||||
From the perspective of high-level synthesis, the temporal structure is equally indispensable: ICS control often involves delay effects, phased operating conditions, and cross-channel coupling, requiring models to be able to characterize low-frequency, long-range dependencies while also overlaying multi-modal fine-grained fluctuations on them. The Transformer series has provided sufficient evidence in long-sequence time series tasks: Transformer-XL breaks through the fixed-length context limitation through a reusable memory mechanism and significantly enhances long-range dependency expression \citep{dai2019transformerxlattentivelanguagemodels}; Informer uses ProbSparse attention and efficient decoding to balance span and efficiency in long-sequence prediction \citep{zhou2021informerefficienttransformerlong}; Autoformer robustly models long-term seasonality and trends through autocorrelation and decomposition mechanisms \citep{wu2022autoformerdecompositiontransformersautocorrelation}; FEDformer further improves long-period prediction performance in frequency domain enhancement and decomposition \citep{zhou2022fedformerfrequencyenhanceddecomposed}; PatchTST enhances the stability and generalization of long-sequence multivariate prediction through local patch-based representation and channel-independent modeling \citep{2023}. Combining our previous positioning of diffusion, this chain of evidence points to a natural division of labor: using attention-based sequence models to first extract stable low-frequency trends/conditions (long-range skeletons), and then allowing diffusion to focus on margins and details in the residual space; meanwhile, discrete masking/absorbing diffusion is applied to supervised/pattern variables to ensure vocabulary legality by construction. This design not only inherits the advantages of time series diffusion in distribution fitting and uncertainty characterization \citep{rasul2021autoregressivedenoisingdiffusionmodels,tashiro2021csdiconditionalscorebaseddiffusion,wen2024diffstgprobabilisticspatiotemporalgraph,liu2023pristiconditionaldiffusionframework,kong2021diffwaveversatilediffusionmodel,11087622}, but also stabilizes the macroscopic temporal support through the long-range attention of Transformer, enabling the formation of an operational integrated generation pipeline under the mixed types and multi-scale dynamics of ICS.
|
||||
|
||||
% 3. Methodology
|
||||
\section{Methodology}
|
||||
\label{sec:method}
|
||||
Industrial control system (ICS) telemetry is intrinsically mixed-type and mechanistically heterogeneous: continuous process trajectories (e.g., sensor and actuator signals) coexist with discrete supervisory states (e.g., modes, alarms, interlocks), and the underlying generating mechanisms range from physical inertia to program-driven step logic. This heterogeneity is not cosmetic—it directly affects what “realistic” synthesis means, because a generator must jointly satisfy (i) temporal coherence, (ii) distributional fidelity, and (iii) discrete semantic validity (i.e., every discrete output must belong to its legal vocabulary by construction). These properties are emphasized broadly in operational-technology security guidance and ICS engineering practice, where state logic and physical dynamics are tightly coupled \citep{nist2023sp80082}.
|
||||
|
||||
We formalize each training instance as a fixed-length window of length We model each training instance as a fixed-length window of length $L$, comprising continuous channels $\bm{X} \in \mathbb{R}^{L \times d_c}$ and discrete channels $\bm{Y} = \{y^{(j)}_{1:L}\}_{j=1}^{d_d}$, where each discrete variable satisfies $y^{(j)}_t \in \mathcal{V}_j$ for a finite vocabulary $\mathcal{V}_j$. Our objective is to learn a generator that produces synthetic $(\hat{\bm{X}}, \hat{\bm{Y}})$ that are simultaneously coherent and distributionally faithful, while also ensuring $\hat{y}^{(j)}_t\in\mathcal{V}_j$ for all $j$, $t$ by construction (rather than via post-hoc rounding or thresholding).
|
||||
|
||||
A key empirical and methodological tension in ICS synthesis is that temporal realism and marginal/distributional realism can compete when optimized monolithically: sequence models trained primarily for regression often over-smooth heavy tails and intermittent bursts, while purely distribution-matching objectives can erode long-range structure. Diffusion models provide a principled route to rich distribution modeling through iterative denoising, but they do not, by themselves, resolve (i) the need for a stable low-frequency temporal scaffold, nor (ii) the discrete legality constraints for supervisory variables \citep{ho2020denoising,song2021score}. Recent time-series diffusion work further suggests that separating coarse structure from stochastic refinement can be an effective inductive bias for long-horizon realism \citep{kollovieh2023tsdiff,sikder2023transfusion}.
|
||||
|
||||
\begin{figure}[htbp]
|
||||
\centering
|
||||
\includegraphics[width=0.8\textwidth]{fig-design-v2.png}
|
||||
% \caption{Description of the figure.}
|
||||
\label{fig:design}
|
||||
\end{figure}
|
||||
|
||||
Motivated by these considerations, we propose Mask-DDPM, organized in the following order:
|
||||
\begin{enumerate}
|
||||
\item Transformer trend module: learns the dominant temporal backbone of continuous dynamics via attention-based sequence modeling \citep{vaswani2017attention}.
|
||||
|
||||
\item Residual DDPM for continuous variables: models distributional detail as stochastic residual structure conditioned on the learned trend \citep{ho2020denoising,kollovieh2023tsdiff}.
|
||||
|
||||
\item Masked diffusion for discrete variables: generates discrete ICS states with an absorbing/masking corruption process and categorical reconstruction \citep{austin2021structured, shi2024simplified}.
|
||||
|
||||
\item Type-aware decomposition: a type-aware factorization and routing layer that assigns variables to the most appropriate modeling mechanism and enforces deterministic constraints where warranted.
|
||||
\end{enumerate}
|
||||
|
||||
This ordering is intentional. The trend module establishes a macro-temporal scaffold; residual diffusion then concentrates capacity on micro-structure and marginal fidelity; masked diffusion provides a native mechanism for discrete legality; and the type-aware layer operationalizes the observation that not all ICS variables should be modeled with the same stochastic mechanism. Importantly, while diffusion-based generation for ICS telemetry has begun to emerge, existing approaches remain limited and typically emphasize continuous synthesis or augmentation; in contrast, our pipeline integrates (i) a Transformer-conditioned residual diffusion backbone, (ii) a discrete masked-diffusion branch, and (iii) explicit type-aware routing for heterogeneous variable mechanisms within a single coherent generator \citep{yuan2025ctu,sha2026ddpm}.
|
||||
|
||||
\subsection{Transformer trend module for continuous dynamics}
|
||||
\label{sec:method-trans}
|
||||
We instantiate the temporal backbone as a causal Transformer trend extractor, leveraging self-attention’s ability to represent long-range dependencies and cross-channel interactions without recurrence \citep{vaswani2017attention}. Compared with recurrent trend extractors (e.g., GRU-style backbones), a Transformer trend module offers a direct mechanism to model delayed effects and multivariate coupling—common in ICS, where control actions may influence downstream sensors with nontrivial lags and regime-dependent propagation \citep{vaswani2017attention,nist2023sp80082}. Crucially, in our design the Transformer is not asked to be the entire generator; instead, it serves a deliberately restricted role: providing a stable, temporally coherent conditioning signal that later stochastic components refine.
|
||||
|
||||
For continuous channels $\bm{X}$, we posit an additive decomposition:
|
||||
\begin{equation}
|
||||
\bm{X} = \bm{S} + \bm{R},
|
||||
\label{eq:additive_decomp}
|
||||
\end{equation}
|
||||
where $\bm{S} \in \mathbb{R}^{L \times d_c}$ is a smooth trend capturing predictable temporal evolution, and $\bm{R} \in \mathbb{R}^{L \times d_c}$ is a residual capturing distributional detail (e.g., bursts, heavy tails, local fluctuations) that is difficult to represent robustly with a purely regression-based temporal objective. This separation reflects an explicit division of labor: the trend module prioritizes temporal coherence, while diffusion (introduced next) targets distributional realism at the residual level—a strategy aligned with “predict-then-refine” perspectives in time-series diffusion modeling \citep{kollovieh2023tsdiff,sikder2023transfusion}.
|
||||
|
||||
We parameterize the trend $\bm{S}$ using a causal Transformer $f_\phi$. With teacher forcing, we train $F_\phi$ to predict the next-step trend from past observations:
|
||||
\begin{equation}
|
||||
\hat{\bm{S}}_{t+1} = f_{\phi}(\bm{X}_{1:t}), \quad t = 1, \dots, L-1.
|
||||
\label{eq:trend_prediction}
|
||||
\end{equation}
|
||||
using the mean-squared error objective:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{trend}}(\phi) = \frac{1}{(L-1)d_c} \sum_{t=1}^{L-1} \bigl\| \hat{\bm{S}}_{t+1} - \bm{X}_{t+1} \bigr\|_2^2.
|
||||
\label{eq:trend_loss}
|
||||
\end{equation}
|
||||
At inference, we roll out the Transformer autoregressively to obtain $\hat{\bm{S}}$, and and then define the residual target for diffusion as $\bm{R} = \bm{X} - \hat{\bm{S}}$. This setup intentionally “locks in” a coherent low-frequency scaffold before any stochastic refinement is applied, thereby reducing the burden on downstream diffusion modules to simultaneously learn both long-range structure and marginal detail. In this sense, our use of Transformers is distinctive: it is a conditioning-first temporal backbone designed to stabilize mixed-type diffusion synthesis in ICS, rather than an end-to-end monolithic generator \citep{vaswani2017attention,kollovieh2023tsdiff,yuan2025ctu}.
|
||||
|
||||
\subsection{DDPM for continuous residual generation}
|
||||
\label{sec:method-ddpm}
|
||||
We model the residual RRR with a denoising diffusion probabilistic model (DDPM) conditioned on the trend $\hat{\bm{S}}$ \citep{ho2020denoising}. Diffusion models learn complex data distributions by inverting a tractable noising process through iterative denoising, and have proven effective at capturing multimodality and heavy-tailed structure that is often attenuated by purely regression-based sequence models \citep{ho2020denoising,song2021score}. Conditioning the diffusion model on $\hat{\bm{S}}$ is central: it prevents the denoiser from re-learning the low-frequency scaffold and focuses capacity on residual micro-structure, mirroring the broader principle that diffusion excels as a distributional corrector when a reasonable coarse structure is available \citep{kollovieh2023tsdiff, sikder2023transfusion}.
|
||||
|
||||
Let $\bm{K}$ denote the number of diffusion steps, with a noise schedule $\{\beta_k\}_{k=1}^K$, $\alpha_k = 1 - \beta_k$, and $\bar{\alpha}_k = \prod_{i=1}^k \alpha_i$. The forward corruption process is:
|
||||
\begin{equation}
|
||||
q(\bm{r}_k \mid \bm{r}_0) &= \mathcal{N}\bigl( \sqrt{\bar{\alpha}_k}\,\bm{r}_0,\; (1 - \bar{\alpha}_k)\mathbf{I} \bigr)
|
||||
\label{eq:forward_corruption}
|
||||
\end{equation}
|
||||
equivalently,
|
||||
\begin{equation}
|
||||
\bm{r}_k &= \sqrt{\bar{\alpha}_k}\,\bm{r}_0 + \sqrt{1 - \bar{\alpha}_k}\,\boldsymbol{\epsilon}, \quad \boldsymbol{\epsilon} \sim \mathcal{N}(\mathbf{0}, \mathbf{I})
|
||||
\label{eq:forward_corruption_eq}
|
||||
\end{equation}
|
||||
The learned reverse process is parameterized as:
|
||||
\begin{equation}
|
||||
p_{\theta}(\bm{r}_{k-1} \mid \bm{r}_k, \hat{\bm{S}}) = \mathcal{N}\bigl( \boldsymbol{\mu}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}),\; \boldsymbol{\Sigma}(k) \bigr).
|
||||
\label{eq:reverse_process}
|
||||
\end{equation}
|
||||
where $\mu_\theta$ is implemented by a Transformer denoiser that consumes (i) the noised residual $r_k$, (ii) a timestep embedding for $k$, and (iii) conditioning features derived from $\hat{\bm{S}}$. This denoiser architecture is consistent with the growing use of attention-based denoisers for long-context time-series diffusion, while our key methodological emphasis is the trend-conditioned residual factorization as the object of diffusion learning \citep{ho2020denoising,sikder2023transfusion}.
|
||||
|
||||
We train the denoiser using the standard DDPM $\epsilon$-prediction objective:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{cont}}(\theta) = \mathbb{E}_{k,\bm{r}_0,\boldsymbol{\epsilon}} \left[ \bigl\| \boldsymbol{\epsilon} - \boldsymbol{\epsilon}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}) \bigr\|_2^2 \right].
|
||||
\label{eq:ddpm_loss}
|
||||
\end{equation}
|
||||
Because diffusion optimization can exhibit timestep imbalance (i.e., some timesteps dominate gradients), we optionally apply an SNR-based reweighting consistent with Min-SNR training:
|
||||
\begin{equation}
|
||||
\mathcal{L}^{\text{snr}}_{\text{cont}}(\theta) = \mathbb{E}_{k,\bm{r}_0,\boldsymbol{\epsilon}} \left[ w_k \bigl\| \boldsymbol{\epsilon} - \boldsymbol{\epsilon}_{\theta}(\bm{r}_k, k, \hat{\bm{S}}) \bigr\|_2^2 \right],
|
||||
\label{eq:snr_loss}
|
||||
\end{equation}
|
||||
where $\mathrm{SNR}_k=\bar{\alpha}_k/(1-\bar{\alpha}_k)$ and $\gamma>0$ is a cap parameter \citep{hang2023efficient}.
|
||||
|
||||
After sampling $\hat{\bm{R}}$ by reverse diffusion, we reconstruct the continuous output as $\hat{\bm{X}} = \hat{\bm{S}} + \hat{\bm{R}}$. Overall, the DDPM component serves as a distributional corrector on top of a temporally coherent backbone, which is particularly suited to ICS where low-frequency dynamics are strong and persistent but fine-scale variability (including bursts and regime-conditioned noise) remains important for realism. Relative to prior ICS diffusion efforts that primarily focus on continuous augmentation, our formulation elevates trend-conditioned residual diffusion as a modular mechanism for disentangling temporal structure from distributional refinement \citep{yuan2025ctu,sha2026ddpm}.
|
||||
|
||||
\subsection{Masked diffusion for discrete ICS variables}
|
||||
\label{sec:method-discrete}
|
||||
Discrete ICS variables must remain categorical, making Gaussian diffusion inappropriate for supervisory states and mode-like channels. While one can attempt continuous relaxations or post-hoc discretization, such strategies risk producing semantically invalid intermediate states (e.g., “in-between” modes) and can distort the discrete marginal distribution. Discrete-state diffusion provides a principled alternative by defining a valid corruption process directly on categorical variables \citep{austin2021structured,shi2024simplified}. In the ICS setting, this is not a secondary detail: supervisory tags often encode control logic boundaries (modes, alarms, interlocks) that must remain within a finite vocabulary to preserve semantic correctness \citep{nist2023sp80082}.
|
||||
|
||||
We therefore adopt masked (absorbing) diffusion for discrete channels, where corruption replaces tokens with a special $\texttt{[MASK]}$ symbol according to a schedule \citep{shi2024simplified}. For each variable $j$, define a masking schedule $\{m_k\}_{k=1}^K$ (with $m_k\in[0,1]$) increasing in $k$. The forward corruption process is:
|
||||
\begin{equation}
|
||||
q(y^{(j)}_k \mid y^{(j)}_0) =
|
||||
\begin{cases}
|
||||
y^{(j)}_0, & \text{with probability } 1 - m_k, \\
|
||||
\texttt{[MASK]}, & \text{with probability } m_k,
|
||||
\end{cases}
|
||||
\label{eq:masking_process}
|
||||
\end{equation}
|
||||
applied independently across $j$ and $t$. Let $\mathcal{M}$ denote the set of masked positions at step $k$. The denoiser $h_{\psi}$ predicts a categorical distribution over $\mathcal{V}_j$ for each masked token, conditioned on (i) the corrupted discrete sequence, (ii) the diffusion step $k$, and (iii) continuous context. Concretely, we condition on $\hat{\bm{S}}$ and $\hat{\bm{X}}$ to couple supervisory reconstruction to the underlying continuous dynamics:
|
||||
\begin{equation}
|
||||
p_{\psi}\bigl( y^{(j)}_0 \mid y_k, k, \hat{\bm{S}}, \hat{\bm{X}} \bigr) = h_{\psi}(y_k, k, \hat{\bm{S}}, \hat{\bm{X}}).
|
||||
\label{eq:discrete_denoising}
|
||||
\end{equation}
|
||||
This conditioning choice is motivated by the fact that many discrete ICS states are not standalone, they are functions of regimes, thresholds, and procedural phases that manifest in continuous channels \citep{nist2023sp80082}. Training uses a categorical denoising objective:
|
||||
\begin{equation}
|
||||
\mathcal{L}_{\text{disc}}(\psi) = \mathbb{E}_{k} \left[ \frac{1}{|\mathcal{M}|} \sum_{(j,t) \in \mathcal{M}} \mathrm{CE}\bigl( h_{\psi}(y_k, k, \hat{\bm{S}}, \hat{\bm{X}})_{j,t},\; y^{(j)}_{0,t} \bigr) \right],
|
||||
\label{eq:discrete_loss}
|
||||
\end{equation}
|
||||
where $\mathrm{CE}(\cdot,\cdot)$ is cross-entropy. At sampling time, we initialize all discrete tokens as $\texttt{[MASK]}$ and iteratively unmask them using the learned conditionals, ensuring that every output token lies in its legal vocabulary by construction. This discrete branch is a key differentiator of our pipeline: unlike typical continuous-only diffusion augmentation in ICS, we integrate masked diffusion as a first-class mechanism for supervisory-variable legality within the same end-to-end synthesis workflow \citep{shi2024simplified,yuan2025ctu}.
|
||||
|
||||
\subsection{Type-aware decomposition as factorization and routing layer}
|
||||
\label{sec:method-types}
|
||||
Even with a trend-conditioned residual DDPM and a discrete masked-diffusion branch, a single uniform modeling treatment can remain suboptimal because ICS variables are generated by qualitatively different mechanisms. For example, program-driven setpoints exhibit step-and-dwell dynamics; controller outputs follow control laws conditioned on process feedback; actuator positions may show saturation and dwell; and some “derived tags” are deterministic functions of other channels. Treating all channels as if they were exchangeable stochastic processes can misallocate model capacity and induce systematic error concentration on a small subset of mechanistically distinct variables \citep{nist2023sp80082}.
|
||||
|
||||
We therefore introduce a type-aware decomposition that formalizes this heterogeneity as a routing and constraint layer. Let $\tau(i)\in{1,\dots,6}$ assign each variable (i) to a type class. The type assignment can be initialized from domain semantics (tag metadata, value domains, and engineering meaning), and subsequently refined via an error-attribution workflow described in the Benchmark section. Importantly, this refinement does not change the core diffusion backbone; it changes which mechanism is responsible for which variable, thereby aligning inductive bias with variable-generating mechanism while preserving overall coherence.
|
||||
|
||||
We use the following taxonomy:
|
||||
\begin{enumerate}
|
||||
\item Type 1 (program-driven / setpoint-like): externally commanded, step-and-dwell variables. These variables can be treated as exogenous drivers (conditioning signals) or routed to specialized change-point / dwell-time models, rather than being forced into a smooth denoiser that may over-regularize step structure.
|
||||
|
||||
\item Type 2 (controller outputs): continuous variables tightly coupled to feedback loops; these benefit from conditional modeling where the conditioning includes relevant process variables and commanded setpoints.
|
||||
|
||||
\item Type 3 (actuator states/positions): often exhibit saturation, dwell, and rate limits; these may require stateful dynamics beyond generic residual diffusion, motivating either specialized conditional modules or additional inductive constraints.
|
||||
|
||||
\item Type 4 (process variables): inertia-dominated continuous dynamics; these are the primary beneficiaries of the Transformer trend + residual DDPM pipeline.
|
||||
|
||||
\item Type 5 (derived/deterministic variables): algebraic or rule-based functions of other variables; we enforce deterministic reconstruction $\hat{x}^{(i)} = g_i(\hat{X},\hat{Y})$ rather than learning a stochastic generator, improving logical consistency and sample efficiency.
|
||||
|
||||
\item Type 6 (auxiliary/low-impact variables): weakly coupled or sparse signals; we allow simplified modeling (e.g., calibrated marginals or lightweight temporal models) to avoid allocating diffusion capacity where it is not warranted.
|
||||
\end{enumerate}
|
||||
|
||||
Type-aware decomposition improves synthesis quality through three mechanisms. First, it improves capacity allocation by preventing a small set of mechanistically atypical variables from dominating gradients and distorting the learned distribution for the majority class (typically Type 4). Second, it enables constraint enforcement by deterministically reconstructing Type 5 variables, preventing logically inconsistent samples that purely learned generators can produce. Third, it improves mechanism alignment by attaching inductive biases consistent with step/dwell or saturation behaviors where generic denoisers may implicitly favor smoothness.
|
||||
|
||||
From a novelty standpoint, this layer is not merely an engineering “patch”; it is an explicit methodological statement that ICS synthesis benefits from typed factorization—a principle that has analogues in mixed-type generative modeling more broadly, but that remains underexplored in diffusion-based ICS telemetry synthesis \citep{shi2025tabdiff,yuan2025ctu,nist2023sp80082}.
|
||||
|
||||
\subsection{Joint optimization and end-to-end sampling}
|
||||
\label{sec:method-joint}
|
||||
We train the model in a staged manner consistent with the above factorization, which improves optimization stability and encourages each component to specialize in its intended role. Specifically: (i) we train the trend Transformer $f_{\phi}$ to obtain $\hat{\bm{S}}$; (ii) we compute residual targets $\hat{\bm{R}} = \bm{X} - \hat{\bm{S}}$ for the continuous variables routed to residual diffusion; (iii) we train the residual DDPM $p_{\theta}(\bm{R}\mid \hat{\bm{S}})$ and masked diffusion model $p_{\psi}(\bm{Y}\mid \text{masked}(\bm{Y}), \hat{\bm{S}}, \hat{\bm{X}})$; and (iv) we apply type-aware routing and deterministic reconstruction during sampling. This staged strategy is aligned with the design goal of separating temporal scaffolding from distributional refinement, and it mirrors the broader intuition in time-series diffusion that decoupling coarse structure and stochastic detail can mitigate “structure vs. realism” conflicts \citep{kollovieh2023tsdiff,sikder2023transfusion}.
|
||||
|
||||
A simple combined objective is $\mathcal{L} = \lambda\mathcal{L}_{\text{cont}} + (1-\lambda)\mathcal{L}_{\text{disc}}$ with $\lambda\in[0,1]$ controlling the balance between continuous and discrete learning. Type-aware routing determines which channels contribute to which loss and which are excluded in favor of deterministic reconstruction. In practice, this routing acts as a principled guardrail against negative transfer across variable mechanisms: channels that are best handled deterministically (Type 5) or by specialized drivers (Type 1/3, depending on configuration) are prevented from forcing the diffusion models into statistically incoherent compromises.
|
||||
|
||||
At inference time, generation follows the same structured order: (i) trend $\hat{\bm{S}}$ via the Transformer, (ii) residual $\hat{\bm{R}}$ via DDPM, (iii) discrete $\hat{\bm{Y}}$ via masked diffusion, and (iv) type-aware assembly with deterministic reconstruction for routed variables. This pipeline produces $(\hat{\bm{X}},\hat{\bm{Y}})$ that are temporally coherent by construction (through $\hat{\bm{S}}$), distributionally expressive (through $\hat{\bm{R}}$ denoising), and discretely valid (through masked diffusion), while explicitly accounting for heterogeneous variable-generating mechanisms through type-aware routing. In combination, these choices constitute our central methodological contribution: a unified Transformer + mixed diffusion generator for ICS telemetry, augmented by typed factorization to align model capacity with domain mechanism \citep{ho2020denoising,shi2024simplified,yuan2025ctu,nist2023sp80082}.
|
||||
|
||||
% 4. Benchmark
|
||||
\section{Benchmark}
|
||||
\label{sec:benchmark}
|
||||
In this section, we present the experimental setup and results.
|
||||
|
||||
% 5. Future Work
|
||||
\section{Future Work}
|
||||
\label{sec:future}
|
||||
In this section, we present the future work.
|
||||
|
||||
% 6. Conclusion
|
||||
\section{Conclusion}
|
||||
\label{sec:conclusion}
|
||||
In this section, we summarize our contributions and future directions.
|
||||
|
||||
% 参考文献
|
||||
\bibliographystyle{unsrtnat}
|
||||
\bibliography{references}
|
||||
|
||||
\end{document}
|
||||
421
arxiv-style/references.bib
Normal file
421
arxiv-style/references.bib
Normal file
@@ -0,0 +1,421 @@
|
||||
@inproceedings{vaswani2017attention,
|
||||
title={Attention Is All You Need},
|
||||
author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, {\L}ukasz and Polosukhin, Illia},
|
||||
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
|
||||
volume={30},
|
||||
year={2017},
|
||||
url={https://arxiv.org/abs/1706.03762}
|
||||
}
|
||||
|
||||
@inproceedings{ho2020denoising,
|
||||
title={Denoising Diffusion Probabilistic Models},
|
||||
author={Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
|
||||
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
|
||||
volume={33},
|
||||
pages={6840--6851},
|
||||
year={2020},
|
||||
url={https://arxiv.org/abs/2006.11239}
|
||||
}
|
||||
|
||||
@inproceedings{austin2021structured,
|
||||
title={Structured Denoising Diffusion Models in Discrete State-Spaces},
|
||||
author={Austin, Jacob and Johnson, Daniel D and Ho, Jonathan and Tarlow, Daniel and van den Berg, Rianne},
|
||||
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
|
||||
volume={34},
|
||||
pages={17981--17993},
|
||||
year={2021},
|
||||
url={https://arxiv.org/abs/2107.03006}
|
||||
}
|
||||
|
||||
@article{shi2024simplified,
|
||||
title={Simplified and Generalized Masked Diffusion for Discrete Data},
|
||||
author={Shi, Juntong and Han, Ke and Wang, Zinan and Doucet, Arnaud and Titsias, Michalis K},
|
||||
journal={arXiv preprint},
|
||||
eprint={2406.04329},
|
||||
archivePrefix={arXiv},
|
||||
year={2024},
|
||||
url={https://arxiv.org/abs/2406.04329}
|
||||
}
|
||||
|
||||
@inproceedings{hang2023efficient,
|
||||
title={Efficient Diffusion Training via Min-SNR Weighting Strategy},
|
||||
author={Hang, Tianyu and Gu, Shuyang and Li, Chen and Bao, Jianmin and Chen, Dong and Hu, Han and Geng, Xin and Guo, Boxin},
|
||||
booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
|
||||
pages={7407--7417},
|
||||
year={2023},
|
||||
doi={10.1109/ICCV51070.2023.00702},
|
||||
url={https://arxiv.org/abs/2303.09556}
|
||||
}
|
||||
|
||||
@inproceedings{kollovieh2023tsdiff,
|
||||
title={Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting},
|
||||
author={Kollovieh, Marcel and Ansari, Abdul Fatir and Bohlke-Schneider, Michael and Fatir Ansari, Abdul and Salinas, David},
|
||||
booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
|
||||
volume={36},
|
||||
year={2023},
|
||||
url={https://arxiv.org/abs/2307.11494}
|
||||
}
|
||||
|
||||
@article{sikder2023transfusion,
|
||||
title={TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers},
|
||||
author={Sikder, M. F. and Ramachandranpillai, R. and Heintz, F.},
|
||||
journal={arXiv preprint},
|
||||
eprint={2307.12667},
|
||||
archivePrefix={arXiv},
|
||||
year={2023},
|
||||
url={https://arxiv.org/abs/2307.12667}
|
||||
}
|
||||
|
||||
@inproceedings{song2021score,
|
||||
title={Score-Based Generative Modeling through Stochastic Differential Equations},
|
||||
author={Song, Yang and Sohl-Dickstein, Jascha and Kingma, Diederik P and Kumar, Abhishek and Ermon, Stefano and Poole, Ben},
|
||||
booktitle={International Conference on Learning Representations (ICLR)},
|
||||
year={2021},
|
||||
url={https://arxiv.org/abs/2011.13456}
|
||||
}
|
||||
|
||||
@inproceedings{shi2025tabdiff,
|
||||
title={TabDiff: A Mixed-type Diffusion Model for Tabular Data Generation},
|
||||
author={Shi, Juntong and Xu, Minkai and Hua, Harper and Zhang, Hengrui and Ermon, Stefano and Leskovec, Jure},
|
||||
booktitle={International Conference on Learning Representations (ICLR)},
|
||||
year={2025},
|
||||
url={https://arxiv.org/abs/2410.20626}
|
||||
}
|
||||
|
||||
@inproceedings{yuan2025ctu,
|
||||
title={CTU-DDPM: Generating Industrial Control System Time-Series Data with a CNN-Transformer Hybrid Diffusion Model},
|
||||
author={Yuan, Yusong and Sha, Yun and Zhao, Wei and Zhang, Kun},
|
||||
booktitle={Proceedings of the 2025 International Symposium on Artificial Intelligence and Computational Social Sciences (ACM AICSS)},
|
||||
pages={123--132},
|
||||
year={2025},
|
||||
doi={10.1145/3776759.3776845},
|
||||
url={https://dl.acm.org/doi/10.1145/3776759.3776845}
|
||||
}
|
||||
|
||||
@misc{sha2026ddpm,
|
||||
title={DDPM Fusing Mamba and Adaptive Attention: An Augmentation Method for Industrial Control Systems Anomaly Data},
|
||||
author={Sha, Yun and Yuan, Yusong and Wu, Yonghao and Zhao, Haidong},
|
||||
year={2026},
|
||||
month={jan},
|
||||
note={SSRN Electronic Journal},
|
||||
eprint={6055903},
|
||||
archivePrefix={SSRN},
|
||||
doi={10.2139/ssrn.6055903},
|
||||
url={https://papers.ssrn.com/sol3/papers.cfm?abstract_id=6055903}
|
||||
}
|
||||
|
||||
@techreport{nist2023sp80082,
|
||||
title={Guide to Operational Technology (OT) Security},
|
||||
author={{National Institute of Standards and Technology}},
|
||||
institution={NIST},
|
||||
type={Special Publication},
|
||||
number={800-82 Rev. 3},
|
||||
year={2023},
|
||||
month={sep},
|
||||
doi={10.6028/NIST.SP.800-82r3},
|
||||
url={https://csrc.nist.gov/pubs/sp/800/82/r3/final}
|
||||
}
|
||||
|
||||
@article{10.1145/1151659.1159928,
|
||||
author = {Vishwanath, Kashi Venkatesh and Vahdat, Amin},
|
||||
title = {Realistic and responsive network traffic generation},
|
||||
year = {2006},
|
||||
issue_date = {October 2006},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
volume = {36},
|
||||
number = {4},
|
||||
issn = {0146-4833},
|
||||
url = {https://doi.org/10.1145/1151659.1159928},
|
||||
doi = {10.1145/1151659.1159928},
|
||||
abstract = {This paper presents Swing, a closed-loop, network-responsive traffic generator that accurately captures the packet interactions of a range of applications using a simple structural model. Starting from observed traffic at a single point in the network, Swing automatically extracts distributions for user, application, and network behavior. It then generates live traffic corresponding to the underlying models in a network emulation environment running commodity network protocol stacks. We find that the generated traces are statistically similar to the original traces. Further, to the best of our knowledge, we are the first to reproduce burstiness in traffic across a range of timescales using a model applicable to a variety of network settings. An initial sensitivity analysis reveals the importance of capturing and recreating user, application, and network characteristics to accurately reproduce such burstiness. Finally, we explore Swing's ability to vary user characteristics, application properties, and wide-area network conditions to project traffic characteristics into alternate scenarios.},
|
||||
journal = {SIGCOMM Comput. Commun. Rev.},
|
||||
month = aug,
|
||||
pages = {111–122},
|
||||
numpages = {12},
|
||||
keywords = {burstiness, energy plot, generator, internet, modeling, structural model, traffic, wavelets}
|
||||
}
|
||||
|
||||
@inproceedings{10.1145/1159913.1159928,
|
||||
author = {Vishwanath, Kashi Venkatesh and Vahdat, Amin},
|
||||
title = {Realistic and responsive network traffic generation},
|
||||
year = {2006},
|
||||
isbn = {1595933085},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
url = {https://doi.org/10.1145/1159913.1159928},
|
||||
doi = {10.1145/1159913.1159928},
|
||||
abstract = {This paper presents Swing, a closed-loop, network-responsive traffic generator that accurately captures the packet interactions of a range of applications using a simple structural model. Starting from observed traffic at a single point in the network, Swing automatically extracts distributions for user, application, and network behavior. It then generates live traffic corresponding to the underlying models in a network emulation environment running commodity network protocol stacks. We find that the generated traces are statistically similar to the original traces. Further, to the best of our knowledge, we are the first to reproduce burstiness in traffic across a range of timescales using a model applicable to a variety of network settings. An initial sensitivity analysis reveals the importance of capturing and recreating user, application, and network characteristics to accurately reproduce such burstiness. Finally, we explore Swing's ability to vary user characteristics, application properties, and wide-area network conditions to project traffic characteristics into alternate scenarios.},
|
||||
booktitle = {Proceedings of the 2006 Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications},
|
||||
pages = {111–122},
|
||||
numpages = {12},
|
||||
keywords = {burstiness, energy plot, generator, internet, modeling, structural model, traffic, wavelets},
|
||||
location = {Pisa, Italy},
|
||||
series = {SIGCOMM '06}
|
||||
}
|
||||
|
||||
@article{Ring_2019,
|
||||
title={Flow-based network traffic generation using Generative Adversarial Networks},
|
||||
volume={82},
|
||||
ISSN={0167-4048},
|
||||
url={http://dx.doi.org/10.1016/j.cose.2018.12.012},
|
||||
DOI={10.1016/j.cose.2018.12.012},
|
||||
journal={Computers & Security},
|
||||
publisher={Elsevier BV},
|
||||
author={Ring, Markus and Schlör, Daniel and Landes, Dieter and Hotho, Andreas},
|
||||
year={2019},
|
||||
month=may, pages={156–172} }
|
||||
|
||||
@inproceedings{10.1145/3544216.3544251,
|
||||
author = {Yin, Yucheng and Lin, Zinan and Jin, Minhao and Fanti, Giulia and Sekar, Vyas},
|
||||
title = {Practical GAN-based synthetic IP header trace generation using NetShare},
|
||||
year = {2022},
|
||||
isbn = {9781450394208},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
url = {https://doi.org/10.1145/3544216.3544251},
|
||||
doi = {10.1145/3544216.3544251},
|
||||
abstract = {We explore the feasibility of using Generative Adversarial Networks (GANs) to automatically learn generative models to generate synthetic packet- and flow header traces for networking tasks (e.g., telemetry, anomaly detection, provisioning). We identify key fidelity, scalability, and privacy challenges and tradeoffs in existing GAN-based approaches. By synthesizing domain-specific insights with recent advances in machine learning and privacy, we identify design choices to tackle these challenges. Building on these insights, we develop an end-to-end framework, NetShare. We evaluate NetShare on six diverse packet header traces and find that: (1) across all distributional metrics and traces, it achieves 46\% more accuracy than baselines and (2) it meets users' requirements of downstream tasks in evaluating accuracy and rank ordering of candidate approaches.},
|
||||
booktitle = {Proceedings of the ACM SIGCOMM 2022 Conference},
|
||||
pages = {458–472},
|
||||
numpages = {15},
|
||||
keywords = {synthetic data generation, privacy, network packets, network flows, generative adversarial networks},
|
||||
location = {Amsterdam, Netherlands},
|
||||
series = {SIGCOMM '22}
|
||||
}
|
||||
|
||||
@inproceedings{Lin_2020, series={IMC ’20},
|
||||
title={Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions},
|
||||
url={http://dx.doi.org/10.1145/3419394.3423643},
|
||||
DOI={10.1145/3419394.3423643},
|
||||
booktitle={Proceedings of the ACM Internet Measurement Conference},
|
||||
publisher={ACM},
|
||||
author={Lin, Zinan and Jain, Alankar and Wang, Chen and Fanti, Giulia and Sekar, Vyas},
|
||||
year={2020},
|
||||
month=oct, pages={464–483},
|
||||
collection={IMC ’20} }
|
||||
|
||||
@INPROCEEDINGS{7469060,
|
||||
author={Mathur, Aditya P. and Tippenhauer, Nils Ole},
|
||||
booktitle={2016 International Workshop on Cyber-physical Systems for Smart Water Networks (CySWater)},
|
||||
title={SWaT: a water treatment testbed for research and training on ICS security},
|
||||
year={2016},
|
||||
volume={},
|
||||
number={},
|
||||
pages={31-36},
|
||||
keywords={Sensors;Actuators;Feeds;Process control;Chemicals;Chemical sensors;Security;Cyber Physical Systems;Industrial Control Systems;Cyber Attacks;Cyber Defense;Water Testbed},
|
||||
doi={10.1109/CySWater.2016.7469060}}
|
||||
|
||||
@inproceedings{10.1145/3055366.3055375,
|
||||
author = {Ahmed, Chuadhry Mujeeb and Palleti, Venkata Reddy and Mathur, Aditya P.},
|
||||
title = {WADI: a water distribution testbed for research in the design of secure cyber physical systems},
|
||||
year = {2017},
|
||||
isbn = {9781450349758},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
url = {https://doi.org/10.1145/3055366.3055375},
|
||||
doi = {10.1145/3055366.3055375},
|
||||
abstract = {The architecture of a water distribution testbed (WADI), and on-going research in the design of secure water distribution system is presented. WADI consists of three stages controlled by Programmable Logic Controllers (PLCs) and two stages controlled via Remote Terminal Units (RTUs). Each PLC and RTU uses sensors to estimate the system state and the actuators to effect control. WADI is currently used to (a) conduct security analysis for water distribution networks, (b) experimentally assess detection mechanisms for potential cyber and physical attacks, and (c) understand how the impact of an attack on one CPS could cascade to other connected CPSs. The cascading effects of attacks can be studied in WADI through its connection to two other testbeds, namely for water treatment and power generation and distribution.},
|
||||
booktitle = {Proceedings of the 3rd International Workshop on Cyber-Physical Systems for Smart Water Networks},
|
||||
pages = {25–28},
|
||||
numpages = {4},
|
||||
keywords = {attack detection, cyber physical systems, cyber security, industrial control systems, water distribution testbed},
|
||||
location = {Pittsburgh, Pennsylvania},
|
||||
series = {CySWATER '17}
|
||||
}
|
||||
|
||||
@inproceedings{NEURIPS2020_4c5bcfec,
|
||||
author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
|
||||
booktitle = {Advances in Neural Information Processing Systems},
|
||||
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
|
||||
pages = {6840--6851},
|
||||
publisher = {Curran Associates, Inc.},
|
||||
title = {Denoising Diffusion Probabilistic Models},
|
||||
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf},
|
||||
volume = {33},
|
||||
year = {2020}
|
||||
}
|
||||
|
||||
@misc{song2021scorebasedgenerativemodelingstochastic,
|
||||
title={Score-Based Generative Modeling through Stochastic Differential Equations},
|
||||
author={Yang Song and Jascha Sohl-Dickstein and Diederik P. Kingma and Abhishek Kumar and Stefano Ermon and Ben Poole},
|
||||
year={2021},
|
||||
eprint={2011.13456},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2011.13456},
|
||||
}
|
||||
|
||||
@misc{rasul2021autoregressivedenoisingdiffusionmodels,
|
||||
title={Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting},
|
||||
author={Kashif Rasul and Calvin Seward and Ingmar Schuster and Roland Vollgraf},
|
||||
year={2021},
|
||||
eprint={2101.12072},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2101.12072},
|
||||
}
|
||||
|
||||
@misc{tashiro2021csdiconditionalscorebaseddiffusion,
|
||||
title={CSDI Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation},
|
||||
author={Yusuke Tashiro and Jiaming Song and Yang Song and Stefano Ermon},
|
||||
year={2021},
|
||||
eprint={2107.03502},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={httpsarxiv.orgabs2107.03502},
|
||||
}
|
||||
|
||||
@misc{wen2024diffstgprobabilisticspatiotemporalgraph,
|
||||
title={DiffSTG: Probabilistic Spatio-Temporal Graph Forecasting with Denoising Diffusion Models},
|
||||
author={Haomin Wen and Youfang Lin and Yutong Xia and Huaiyu Wan and Qingsong Wen and Roger Zimmermann and Yuxuan Liang},
|
||||
year={2024},
|
||||
eprint={2301.13629},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2301.13629},
|
||||
}
|
||||
|
||||
@misc{liu2023pristiconditionaldiffusionframework,
|
||||
title={PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputation},
|
||||
author={Mingzhe Liu and Han Huang and Hao Feng and Leilei Sun and Bowen Du and Yanjie Fu},
|
||||
year={2023},
|
||||
eprint={2302.09746},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2302.09746},
|
||||
}
|
||||
|
||||
@misc{kong2021diffwaveversatilediffusionmodel,
|
||||
title={DiffWave: A Versatile Diffusion Model for Audio Synthesis},
|
||||
author={Zhifeng Kong and Wei Ping and Jiaji Huang and Kexin Zhao and Bryan Catanzaro},
|
||||
year={2021},
|
||||
eprint={2009.09761},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={eess.AS},
|
||||
url={https://arxiv.org/abs/2009.09761},
|
||||
}
|
||||
|
||||
@ARTICLE{11087622,
|
||||
author={Liu, Xiaosi and Xu, Xiaowen and Liu, Zhidan and Li, Zhenjiang and Wu, Kaishun},
|
||||
journal={IEEE Transactions on Mobile Computing},
|
||||
title={Spatio-Temporal Diffusion Model for Cellular Traffic Generation},
|
||||
year={2026},
|
||||
volume={25},
|
||||
number={1},
|
||||
pages={257-271},
|
||||
keywords={Base stations;Diffusion models;Data models;Uncertainty;Predictive models;Generative adversarial networks;Knowledge graphs;Mobile computing;Telecommunication traffic;Semantics;Cellular traffic;data generation;diffusion model;spatio-temporal graph},
|
||||
doi={10.1109/TMC.2025.3591183}}
|
||||
|
||||
@misc{austin2023structureddenoisingdiffusionmodels,
|
||||
title={Structured Denoising Diffusion Models in Discrete State-Spaces},
|
||||
author={Jacob Austin and Daniel D. Johnson and Jonathan Ho and Daniel Tarlow and Rianne van den Berg},
|
||||
year={2023},
|
||||
eprint={2107.03006},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2107.03006},
|
||||
}
|
||||
|
||||
@misc{li2022diffusionlmimprovescontrollabletext,
|
||||
title={Diffusion-LM Improves Controllable Text Generation},
|
||||
author={Xiang Lisa Li and John Thickstun and Ishaan Gulrajani and Percy Liang and Tatsunori B. Hashimoto},
|
||||
year={2022},
|
||||
eprint={2205.14217},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={httpsarxiv.orgabs2205.14217},
|
||||
}
|
||||
|
||||
@misc{meng2025aflnetyearslatercoverageguided,
|
||||
title={AFLNet Five Years Later: On Coverage-Guided Protocol Fuzzing},
|
||||
author={Ruijie Meng and Van-Thuan Pham and Marcel Böhme and Abhik Roychoudhury},
|
||||
year={2025},
|
||||
eprint={2412.20324},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.SE},
|
||||
url={https://arxiv.org/abs/2412.20324},
|
||||
}
|
||||
|
||||
@misc{godefroid2017learnfuzzmachinelearninginput,
|
||||
title={Learn&Fuzz: Machine Learning for Input Fuzzing},
|
||||
author={Patrice Godefroid and Hila Peleg and Rishabh Singh},
|
||||
year={2017},
|
||||
eprint={1701.07232},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.AI},
|
||||
url={https://arxiv.org/abs/1701.07232},
|
||||
}
|
||||
|
||||
@misc{she2019neuzzefficientfuzzingneural,
|
||||
title={NEUZZ: Efficient Fuzzing with Neural Program Smoothing},
|
||||
author={Dongdong She and Kexin Pei and Dave Epstein and Junfeng Yang and Baishakhi Ray and Suman Jana},
|
||||
year={2019},
|
||||
eprint={1807.05620},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CR},
|
||||
url={https://arxiv.org/abs/1807.05620},
|
||||
}
|
||||
|
||||
@misc{hoogeboom2021argmaxflowsmultinomialdiffusion,
|
||||
title={Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions},
|
||||
author={Emiel Hoogeboom and Didrik Nielsen and Priyank Jaini and Patrick Forré and Max Welling},
|
||||
year={2021},
|
||||
eprint={2102.05379},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={stat.ML},
|
||||
url={https://arxiv.org/abs/2102.05379},
|
||||
}
|
||||
|
||||
@misc{dai2019transformerxlattentivelanguagemodels,
|
||||
title={Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context},
|
||||
author={Zihang Dai and Zhilin Yang and Yiming Yang and Jaime Carbonell and Quoc V. Le and Ruslan Salakhutdinov},
|
||||
year={2019},
|
||||
eprint={1901.02860},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/1901.02860},
|
||||
}
|
||||
|
||||
@misc{zhou2021informerefficienttransformerlong,
|
||||
title={Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting},
|
||||
author={Haoyi Zhou and Shanghang Zhang and Jieqi Peng and Shuai Zhang and Jianxin Li and Hui Xiong and Wancai Zhang},
|
||||
year={2021},
|
||||
eprint={2012.07436},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2012.07436},
|
||||
}
|
||||
|
||||
@misc{wu2022autoformerdecompositiontransformersautocorrelation,
|
||||
title={Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting},
|
||||
author={Haixu Wu and Jiehui Xu and Jianmin Wang and Mingsheng Long},
|
||||
year={2022},
|
||||
eprint={2106.13008},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2106.13008},
|
||||
}
|
||||
|
||||
@misc{zhou2022fedformerfrequencyenhanceddecomposed,
|
||||
title={FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting},
|
||||
author={Tian Zhou and Ziqing Ma and Qingsong Wen and Xue Wang and Liang Sun and Rong Jin},
|
||||
year={2022},
|
||||
eprint={2201.12740},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.LG},
|
||||
url={https://arxiv.org/abs/2201.12740},
|
||||
}
|
||||
|
||||
@article{2023,
|
||||
title={A Note on Extremal Sombor Indices of Trees with a Given Degree Sequence},
|
||||
volume={90},
|
||||
ISSN={0340-6253},
|
||||
url={http://dx.doi.org/10.46793/match.90-1.197D},
|
||||
DOI={10.46793/match.90-1.197d},
|
||||
number={1},
|
||||
journal={Match Communications in Mathematical and in Computer Chemistry},
|
||||
publisher={University Library in Kragujevac},
|
||||
author={Damjanović, Ivan and Milošević, Marko and Stevanović, Dragan},
|
||||
year={2023},
|
||||
pages={197–202} }
|
||||
214
arxiv-style/template.tex
Normal file
214
arxiv-style/template.tex
Normal file
@@ -0,0 +1,214 @@
|
||||
\documentclass{article}
|
||||
|
||||
\usepackage{arxiv}
|
||||
|
||||
\usepackage[utf8]{inputenc} % allow utf-8 input
|
||||
\usepackage[T1]{fontenc} % use 8-bit T1 fonts
|
||||
\usepackage{hyperref} % hyperlinks
|
||||
\usepackage{url} % simple URL typesetting
|
||||
\usepackage{booktabs} % professional-quality tables
|
||||
\usepackage{amsfonts} % blackboard math symbols
|
||||
\usepackage{nicefrac} % compact symbols for 1/2, etc.
|
||||
\usepackage{microtype} % microtypography
|
||||
\usepackage{cleveref} % smart cross-referencing
|
||||
\usepackage{lipsum} % Can be removed after putting your text content
|
||||
\usepackage{graphicx}
|
||||
\usepackage{natbib}
|
||||
\usepackage{doi}
|
||||
|
||||
\title{A template for the \emph{arxiv} style}
|
||||
|
||||
% Here you can change the date presented in the paper title
|
||||
%\date{September 9, 1985}
|
||||
% Or remove it
|
||||
%\date{}
|
||||
|
||||
\newif\ifuniqueAffiliation
|
||||
% Comment to use multiple affiliations variant of author block
|
||||
\uniqueAffiliationtrue
|
||||
|
||||
\ifuniqueAffiliation % Standard variant of author block
|
||||
\author{ \href{https://orcid.org/0000-0000-0000-0000}{\includegraphics[scale=0.06]{orcid.pdf}\hspace{1mm}David S.~Hippocampus}\thanks{Use footnote for providing further
|
||||
information about author (webpage, alternative
|
||||
address)---\emph{not} for acknowledging funding agencies.} \\
|
||||
Department of Computer Science\\
|
||||
Cranberry-Lemon University\\
|
||||
Pittsburgh, PA 15213 \\
|
||||
\texttt{hippo@cs.cranberry-lemon.edu} \\
|
||||
%% examples of more authors
|
||||
\And
|
||||
\href{https://orcid.org/0000-0000-0000-0000}{\includegraphics[scale=0.06]{orcid.pdf}\hspace{1mm}Elias D.~Striatum} \\
|
||||
Department of Electrical Engineering\\
|
||||
Mount-Sheikh University\\
|
||||
Santa Narimana, Levand \\
|
||||
\texttt{stariate@ee.mount-sheikh.edu} \\
|
||||
%% \AND
|
||||
%% Coauthor \\
|
||||
%% Affiliation \\
|
||||
%% Address \\
|
||||
%% \texttt{email} \\
|
||||
%% \And
|
||||
%% Coauthor \\
|
||||
%% Affiliation \\
|
||||
%% Address \\
|
||||
%% \texttt{email} \\
|
||||
%% \And
|
||||
%% Coauthor \\
|
||||
%% Affiliation \\
|
||||
%% Address \\
|
||||
%% \texttt{email} \\
|
||||
}
|
||||
\else
|
||||
% Multiple affiliations variant of author block
|
||||
\usepackage{authblk}
|
||||
\renewcommand\Authfont{\bfseries}
|
||||
\setlength{\affilsep}{0em}
|
||||
% box is needed for correct spacing with authblk
|
||||
\newbox{\orcid}\sbox{\orcid}{\includegraphics[scale=0.06]{orcid.pdf}}
|
||||
\author[1]{%
|
||||
\href{https://orcid.org/0000-0000-0000-0000}{\usebox{\orcid}\hspace{1mm}David S.~Hippocampus\thanks{\texttt{hippo@cs.cranberry-lemon.edu}}}%
|
||||
}
|
||||
\author[1,2]{%
|
||||
\href{https://orcid.org/0000-0000-0000-0000}{\usebox{\orcid}\hspace{1mm}Elias D.~Striatum\thanks{\texttt{stariate@ee.mount-sheikh.edu}}}%
|
||||
}
|
||||
\affil[1]{Department of Computer Science, Cranberry-Lemon University, Pittsburgh, PA 15213}
|
||||
\affil[2]{Department of Electrical Engineering, Mount-Sheikh University, Santa Narimana, Levand}
|
||||
\fi
|
||||
|
||||
% Uncomment to override the `A preprint' in the header
|
||||
%\renewcommand{\headeright}{Technical Report}
|
||||
%\renewcommand{\undertitle}{Technical Report}
|
||||
\renewcommand{\shorttitle}{\textit{arXiv} Template}
|
||||
|
||||
%%% Add PDF metadata to help others organize their library
|
||||
%%% Once the PDF is generated, you can check the metadata with
|
||||
%%% $ pdfinfo template.pdf
|
||||
\hypersetup{
|
||||
pdftitle={A template for the arxiv style},
|
||||
pdfsubject={q-bio.NC, q-bio.QM},
|
||||
pdfauthor={David S.~Hippocampus, Elias D.~Striatum},
|
||||
pdfkeywords={First keyword, Second keyword, More},
|
||||
}
|
||||
|
||||
\begin{document}
|
||||
\maketitle
|
||||
|
||||
\begin{abstract}
|
||||
\lipsum[1]
|
||||
\end{abstract}
|
||||
|
||||
|
||||
% keywords can be removed
|
||||
\keywords{First keyword \and Second keyword \and More}
|
||||
|
||||
|
||||
\section{Introduction}
|
||||
\lipsum[2]
|
||||
\lipsum[3]
|
||||
|
||||
|
||||
\section{Headings: first level}
|
||||
\label{sec:headings}
|
||||
|
||||
\lipsum[4] See Section \ref{sec:headings}.
|
||||
|
||||
\subsection{Headings: second level}
|
||||
\lipsum[5]
|
||||
\begin{equation}
|
||||
\xi _{ij}(t)=P(x_{t}=i,x_{t+1}=j|y,v,w;\theta)= {\frac {\alpha _{i}(t)a^{w_t}_{ij}\beta _{j}(t+1)b^{v_{t+1}}_{j}(y_{t+1})}{\sum _{i=1}^{N} \sum _{j=1}^{N} \alpha _{i}(t)a^{w_t}_{ij}\beta _{j}(t+1)b^{v_{t+1}}_{j}(y_{t+1})}}
|
||||
\end{equation}
|
||||
|
||||
\subsubsection{Headings: third level}
|
||||
\lipsum[6]
|
||||
|
||||
\paragraph{Paragraph}
|
||||
\lipsum[7]
|
||||
|
||||
|
||||
|
||||
\section{Examples of citations, figures, tables, references}
|
||||
\label{sec:others}
|
||||
|
||||
\subsection{Citations}
|
||||
Citations use \verb+natbib+. The documentation may be found at
|
||||
\begin{center}
|
||||
\url{http://mirrors.ctan.org/macros/latex/contrib/natbib/natnotes.pdf}
|
||||
\end{center}
|
||||
|
||||
Here is an example usage of the two main commands (\verb+citet+ and \verb+citep+): Some people thought a thing \citep{kour2014real, keshet2016prediction} but other people thought something else \citep{kour2014fast}. Many people have speculated that if we knew exactly why \citet{kour2014fast} thought this\dots
|
||||
|
||||
\subsection{Figures}
|
||||
\lipsum[10]
|
||||
See Figure \ref{fig:fig1}. Here is how you add footnotes. \footnote{Sample of the first footnote.}
|
||||
\lipsum[11]
|
||||
|
||||
\begin{figure}
|
||||
\centering
|
||||
\fbox{\rule[-.5cm]{4cm}{4cm} \rule[-.5cm]{4cm}{0cm}}
|
||||
\caption{Sample figure caption.}
|
||||
\label{fig:fig1}
|
||||
\end{figure}
|
||||
|
||||
\subsection{Tables}
|
||||
See awesome Table~\ref{tab:table}.
|
||||
|
||||
The documentation for \verb+booktabs+ (`Publication quality tables in LaTeX') is available from:
|
||||
\begin{center}
|
||||
\url{https://www.ctan.org/pkg/booktabs}
|
||||
\end{center}
|
||||
|
||||
|
||||
\begin{table}
|
||||
\caption{Sample table title}
|
||||
\centering
|
||||
\begin{tabular}{lll}
|
||||
\toprule
|
||||
\multicolumn{2}{c}{Part} \\
|
||||
\cmidrule(r){1-2}
|
||||
Name & Description & Size ($\mu$m) \\
|
||||
\midrule
|
||||
Dendrite & Input terminal & $\sim$100 \\
|
||||
Axon & Output terminal & $\sim$10 \\
|
||||
Soma & Cell body & up to $10^6$ \\
|
||||
\bottomrule
|
||||
\end{tabular}
|
||||
\label{tab:table}
|
||||
\end{table}
|
||||
|
||||
\subsection{Lists}
|
||||
\begin{itemize}
|
||||
\item Lorem ipsum dolor sit amet
|
||||
\item consectetur adipiscing elit.
|
||||
\item Aliquam dignissim blandit est, in dictum tortor gravida eget. In ac rutrum magna.
|
||||
\end{itemize}
|
||||
|
||||
|
||||
\bibliographystyle{unsrtnat}
|
||||
\bibliography{references} %%% Uncomment this line and comment out the ``thebibliography'' section below to use the external .bib file (using bibtex) .
|
||||
|
||||
|
||||
%%% Uncomment this section and comment out the \bibliography{references} line above to use inline references.
|
||||
% \begin{thebibliography}{1}
|
||||
|
||||
% \bibitem{kour2014real}
|
||||
% George Kour and Raid Saabne.
|
||||
% \newblock Real-time segmentation of on-line handwritten arabic script.
|
||||
% \newblock In {\em Frontiers in Handwriting Recognition (ICFHR), 2014 14th
|
||||
% International Conference on}, pages 417--422. IEEE, 2014.
|
||||
|
||||
% \bibitem{kour2014fast}
|
||||
% George Kour and Raid Saabne.
|
||||
% \newblock Fast classification of handwritten on-line arabic characters.
|
||||
% \newblock In {\em Soft Computing and Pattern Recognition (SoCPaR), 2014 6th
|
||||
% International Conference of}, pages 312--318. IEEE, 2014.
|
||||
|
||||
% \bibitem{keshet2016prediction}
|
||||
% Keshet, Renato, Alina Maor, and George Kour.
|
||||
% \newblock Prediction-Based, Prioritized Market-Share Insight Extraction.
|
||||
% \newblock In {\em Advanced Data Mining and Applications (ADMA), 2016 12th International
|
||||
% Conference of}, pages 81--94,2016.
|
||||
|
||||
% \end{thebibliography}
|
||||
|
||||
|
||||
\end{document}
|
||||
Reference in New Issue
Block a user