ModuFlow/internal-docs
3
0
Fork 0
forked from manbo/internal-docs
Code Pull Requests Activity

Improve layout and spacing; add enumitem

Browse Source 
Update main.tex to tighten internal spacing and list formatting: add \usepackage{enumitem}, set compact float spacing (\textfloatsep, \floatsep, \intextsep, \abovecaptionskip, \belowcaptionskip), and configure \setlist for denser lists; enable \raggedbottom. Adjust figure include to 0.995\textwidth with trim+clip to avoid overfull boxes. Make small editorial tweaks ("time-step" hyphenation and minor rephrasing in the Conclusion). Recompiled artifacts (main.aux, main.log, main.pdf) were also updated.
This commit is contained in:
Markyan04
2026-04-21 14:40:48 +08:00
parent c4ff6c5df4
commit 0ed8318821
4 changed files with 100 additions and 112 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
LaTeX2e+Proceedings+Templates+download/main.tex
View File

@@ -10,8 +10,17 @@
\usepackage{booktabs}
\usepackage[expansion=false]{microtype}
\usepackage{float}
\usepackage{enumitem}
\usepackage{url}
% Compact internal spacing only; page layout/margins remain unchanged.
\setlength{\textfloatsep}{10pt plus 2pt minus 2pt}
\setlength{\floatsep}{8pt plus 2pt minus 2pt}
\setlength{\intextsep}{10pt plus 2pt minus 2pt}
\setlength{\abovecaptionskip}{4pt}
\setlength{\belowcaptionskip}{0pt}
\setlist{topsep=3pt,itemsep=2pt,parsep=0pt,partopsep=0pt}
% Compatibility shim: the source manuscript uses natbib-style citep commands.
\newcommand{\citep}[1]{\cite{#1}}
@@ -28,6 +37,7 @@ School of Artificial Intelligence, South China Normal University, Guangzhou, Gua
\email{huan.yang@m.scnu.edu.cn}}
\begin{document}
\raggedbottom
\maketitle
\begin{abstract}
@@ -68,7 +78,7 @@ A key empirical and methodological tension in ICS synthesis is that temporal rea
\begin{figure}[htbp]
\centering
\includegraphics[width=0.8\textwidth]{fig-design-v4-from-user-svg-cropped.pdf}
\includegraphics[width=0.995\textwidth,trim=4pt 4pt 4pt 4pt,clip]{fig-design-v4-from-user-svg-cropped.pdf}
\caption{Masked-DDPM: Unified Synthesis for ICS traffic}
\label{fig:design}
\end{figure}
@@ -135,7 +145,7 @@ We train the denoiser using the standard DDPM $\epsilon$-prediction objective:
\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:
Because diffusion optimization can exhibit time-step imbalance (i.e., some steps 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}
@@ -317,9 +327,9 @@ Taken together, the benchmark supports a focused claim. Mask-DDPM already provid
% 5. Conclusion and Future Work
\section{Conclusion and Future Work}
\label{sec:conclusion}
This paper addresses the data scarcity and shareability barriers that limit machine-learning research for industrial control systems (ICS) security by proposing Mask-DDPM, a hybrid synthetic telemetry generator at the protocol-feature level. By combining a causal Transformer trend module, a trend-conditioned residual DDPM, a masked diffusion branch for discrete variables, and a type-aware routing layer, the framework preserves long-horizon temporal structure, improves local distributional fidelity, and guarantees discrete semantic legality. On windows derived from the HAI Security Dataset, the model achieves stable mixed-type fidelity across seeds, with mean KS = 0.3311 $\pm$ 0.0079 on continuous features, mean JSD = 0.0284 $\pm$ 0.0073 on discrete features, and mean absolute lag-1 autocorrelation difference = 0.2684 $\pm$ 0.0027.
This paper addresses data scarcity and sharing barriers in industrial control systems (ICS) security by proposing Mask-DDPM, a hybrid synthetic telemetry generator at the protocol-feature level. By combining a causal Transformer trend module, a trend-conditioned residual DDPM, a masked diffusion branch for discrete variables, and a type-aware routing layer, the framework preserves long-horizon temporal structure, improves local distributional fidelity, and guarantees discrete semantic legality. On windows derived from the HAI Security Dataset, the model achieves stable mixed-type fidelity across seeds, with mean KS = 0.3311 $\pm$ 0.0079 on continuous features, mean JSD = 0.0284 $\pm$ 0.0073 on discrete features, and mean absolute lag-1 autocorrelation difference = 0.2684 $\pm$ 0.0027.
Overall, Mask-DDPM provides a reproducible foundation for generating shareable and semantically valid ICS feature sequences for data augmentation, benchmarking, and downstream packet/trace reconstruction workflows. Future work will proceed in two complementary directions. Vertically, we will strengthen the theoretical foundation of the framework by introducing more explicit control-theoretic constraints, structured state-space or causal priors, and formal transition models for supervisory logic, so that legality, stability, and cross-channel coupling can be characterized more rigorously. Horizontally, we will extend the framework beyond the current setting to additional industrial control protocols such as Modbus/TCP, DNP3, IEC 104, and OPC UA, and investigate analogous adaptations to automotive communication protocols such as CAN/CAN FD and automotive Ethernet. A related extension is controllable attack or violation injection on top of legal base traces, enabling reproducible adversarial benchmarks for anomaly detection and intrusion-detection studies.
Overall, Mask-DDPM provides a reproducible foundation for shareable, semantically valid ICS feature sequences for data augmentation, benchmarking, and downstream packet/trace reconstruction workflows. Future work will proceed in two complementary directions. Vertically, we will strengthen the theoretical foundation of the framework by introducing more explicit control-theoretic constraints, structured state-space or causal priors, and formal transition models for supervisory logic, so that legality, stability, and cross-channel coupling can be characterized more rigorously. Horizontally, we will extend the framework beyond the current setting to additional industrial control protocols such as Modbus/TCP, DNP3, IEC 104, and OPC UA, and investigate analogous adaptations to automotive communication protocols such as CAN/CAN FD and automotive Ethernet. A related extension is controllable attack or violation injection on top of legal base traces, enabling reproducible adversarial benchmarks for anomaly detection and intrusion-detection studies.
\bibliographystyle{splncs04}
\bibliography{references}