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

12
LaTeX2e+Proceedings+Templates+download/main.aux
View File

@@ -99,23 +99,23 @@
\newlabel{fig:benchmark_story}{{3}{13}{}{figure.3}{}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Core benchmark summary. Lower is better except for validity rate.}}{13}{}\protected@file@percent }
\newlabel{tab:core_metrics}{{1}{13}{}{table.1}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Type-aware diagnostics}{14}{}\protected@file@percent }
\newlabel{sec:benchmark-typed}{{4.2}{14}{}{subsection.4.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.2}Type-aware diagnostics}{13}{}\protected@file@percent }
\newlabel{sec:benchmark-typed}{{4.2}{13}{}{subsection.4.2}{}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Type-aware diagnostic summary. Lower values indicate better alignment.}}{14}{}\protected@file@percent }
\newlabel{tab:typed_diagnostics}{{2}{14}{}{table.2}{}}
\@writefile{toc}{\contentsline {subsection}{\numberline {4.3}Ablation study}{14}{}\protected@file@percent }
\newlabel{sec:benchmark-ablation}{{4.3}{14}{}{subsection.4.3}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces Ablation impact.}}{15}{}\protected@file@percent }
\newlabel{fig:ablation_impact}{{4}{15}{}{figure.4}{}}
\@writefile{lof}{\contentsline {figure}{\numberline {4}{\ignorespaces Ablation impact.}}{14}{}\protected@file@percent }
\newlabel{fig:ablation_impact}{{4}{14}{}{figure.4}{}}
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces Ablation study. Lower is better except for anomaly AUPRC.}}{15}{}\protected@file@percent }
\newlabel{tab:ablation}{{3}{15}{}{table.3}{}}
\@writefile{toc}{\contentsline {section}{\numberline {5}Conclusion and Future Work}{15}{}\protected@file@percent }
\newlabel{sec:conclusion}{{5}{15}{}{section.5}{}}
\bibstyle{splncs04}
\bibdata{references}
\bibcite{10.1145/3055366.3055375}{1}
\bibcite{info16100910}{2}
\bibcite{austin2021structured}{3}
\@writefile{toc}{\contentsline {section}{\numberline {5}Conclusion and Future Work}{16}{}\protected@file@percent }
\newlabel{sec:conclusion}{{5}{16}{}{section.5}{}}
\bibcite{coletta2023constrained}{4}
\bibcite{dai2019transformerxlattentivelanguagemodels}{5}
\bibcite{godefroid2017learnfuzzmachinelearninginput}{6}

182
LaTeX2e+Proceedings+Templates+download/main.log
View File

@@ -1,4 +1,4 @@
This is pdfTeX, Version 3.141592653-2.6-1.40.28 (MiKTeX 25.12) (preloaded format=pdflatex 2026.4.14) 21 APR 2026 14:14
This is pdfTeX, Version 3.141592653-2.6-1.40.28 (MiKTeX 25.12) (preloaded format=pdflatex 2026.4.14) 21 APR 2026 14:35
entering extended mode
restricted \write18 enabled.
%&-line parsing enabled.
@@ -374,49 +374,58 @@ Package: float 2001/11/08 v1.3d Float enhancements (AL)
\@float@everytoks=\toks31
\@floatcapt=\box107
)
(C:\Users\Markyan04\AppData\Roaming\MiKTeX\tex/latex/enumitem\enumitem.sty
Package: enumitem 2025/02/06 v3.11 Customized lists
\labelindent=\skip59
\enit@outerparindent=\dimen198
\enit@toks=\toks32
\enit@inbox=\box108
\enit@count@id=\count334
\enitdp@description=\count335
)
(D:\MikTex\tex/latex/url\url.sty
\Urlmuskip=\muskip18
Package: url 2013/09/16 ver 3.4 Verb mode for urls, etc.
)
LaTeX Font Info: Trying to load font information for T1+lmr on input line 30
LaTeX Font Info: Trying to load font information for T1+lmr on input line 39
.
(D:\MikTex\tex/latex/lm\t1lmr.fd
File: t1lmr.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
)
(D:\MikTex\tex/latex/l3backend\l3backend-pdftex.def
File: l3backend-pdftex.def 2025-10-09 L3 backend support: PDF output (pdfTeX)
\l__color_backend_stack_int=\count334
\l__color_backend_stack_int=\count336
) (main.aux)
\openout1 = `main.aux'.
LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for OMS/cmsy/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for OT1/cmr/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for T1/cmr/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for TS1/cmr/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for OMX/cmex/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for U/cmr/m/n on input line 30.
LaTeX Font Info: ... okay on input line 30.
LaTeX Font Info: Checking defaults for OML/cmm/m/it on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for OMS/cmsy/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for OT1/cmr/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for T1/cmr/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for TS1/cmr/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for OMX/cmex/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
LaTeX Font Info: Checking defaults for U/cmr/m/n on input line 39.
LaTeX Font Info: ... okay on input line 39.
(D:\MikTex\tex/context/base/mkii\supp-pdf.mkii
[Loading MPS to PDF converter (version 2006.09.02).]
\scratchcounter=\count335
\scratchdimen=\dimen198
\scratchbox=\box108
\nofMPsegments=\count336
\nofMParguments=\count337
\everyMPshowfont=\toks32
\MPscratchCnt=\count338
\MPscratchDim=\dimen199
\MPnumerator=\count339
\makeMPintoPDFobject=\count340
\everyMPtoPDFconversion=\toks33
\scratchcounter=\count337
\scratchdimen=\dimen199
\scratchbox=\box109
\nofMPsegments=\count338
\nofMParguments=\count339
\everyMPshowfont=\toks33
\MPscratchCnt=\count340
\MPscratchDim=\dimen256
\MPnumerator=\count341
\makeMPintoPDFobject=\count342
\everyMPtoPDFconversion=\toks34
) (D:\MikTex\tex/latex/epstopdf-pkg\epstopdf-base.sty
Package: epstopdf-base 2020-01-24 v2.11 Base part for package epstopdf
Package epstopdf-base Info: Redefining graphics rule for `.eps' on input line 4
@@ -425,13 +434,13 @@ Package epstopdf-base Info: Redefining graphics rule for `.eps' on input line 4
(D:\MikTex\tex/latex/00miktex\epstopdf-sys.cfg
File: epstopdf-sys.cfg 2021/03/18 v2.0 Configuration of epstopdf for MiKTeX
))
LaTeX Info: Redefining \microtypecontext on input line 30.
Package microtype Info: Applying patch `item' on input line 30.
Package microtype Info: Applying patch `toc' on input line 30.
Package microtype Info: Applying patch `eqnum' on input line 30.
Package microtype Info: Applying patch `footnote' on input line 30.
Package microtype Info: Applying patch `verbatim' on input line 30.
LaTeX Info: Redefining \microtypesetup on input line 30.
LaTeX Info: Redefining \microtypecontext on input line 39.
Package microtype Info: Applying patch `item' on input line 39.
Package microtype Info: Applying patch `toc' on input line 39.
Package microtype Info: Applying patch `eqnum' on input line 39.
Package microtype Info: Applying patch `footnote' on input line 39.
Package microtype Info: Applying patch `verbatim' on input line 39.
LaTeX Info: Redefining \microtypesetup on input line 39.
Package microtype Info: Generating PDF output.
Package microtype Info: Character protrusion enabled (level 2).
Package microtype Info: Using default protrusion set `alltext'.
@@ -444,35 +453,35 @@ Package microtype Info: No adjustment of character kerning.
File: mt-cmr.cfg 2013/05/19 v2.2 microtype config. file: Computer Modern Roman
(RS)
)
LaTeX Font Info: Trying to load font information for OT1+lmr on input line 3
LaTeX Font Info: Trying to load font information for OT1+lmr on input line 4
1.
(D:\MikTex\tex/latex/lm\ot1lmr.fd
File: ot1lmr.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
)
LaTeX Font Info: Trying to load font information for OML+lmm on input line 3
LaTeX Font Info: Trying to load font information for OML+lmm on input line 4
1.
(D:\MikTex\tex/latex/lm\omllmm.fd
File: omllmm.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
)
LaTeX Font Info: Trying to load font information for OMS+lmsy on input line
31.
41.
(D:\MikTex\tex/latex/lm\omslmsy.fd
File: omslmsy.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
)
LaTeX Font Info: Trying to load font information for OMX+lmex on input line
31.
41.
(D:\MikTex\tex/latex/lm\omxlmex.fd
File: omxlmex.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
)
LaTeX Font Info: External font `lmex10' loaded for size
(Font) <10> on input line 31.
(Font) <10> on input line 41.
LaTeX Font Info: External font `lmex10' loaded for size
(Font) <7> on input line 31.
(Font) <7> on input line 41.
LaTeX Font Info: External font `lmex10' loaded for size
(Font) <5> on input line 31.
LaTeX Font Info: Trying to load font information for U+msa on input line 31.
(Font) <5> on input line 41.
LaTeX Font Info: Trying to load font information for U+msa on input line 41.
(D:\MikTex\tex/latex/amsfonts\umsa.fd
@@ -481,7 +490,7 @@ File: umsa.fd 2013/01/14 v3.01 AMS symbols A
(C:\Users\Markyan04\AppData\Roaming\MiKTeX\tex/latex/microtype\mt-msa.cfg
File: mt-msa.cfg 2006/02/04 v1.1 microtype config. file: AMS symbols (a) (RS)
)
LaTeX Font Info: Trying to load font information for U+msb on input line 31.
LaTeX Font Info: Trying to load font information for U+msb on input line 41.
(D:\MikTex\tex/latex/amsfonts\umsb.fd
@@ -490,7 +499,7 @@ File: umsb.fd 2013/01/14 v3.01 AMS symbols B
(C:\Users\Markyan04\AppData\Roaming\MiKTeX\tex/latex/microtype\mt-msb.cfg
File: mt-msb.cfg 2005/06/01 v1.0 microtype config. file: AMS symbols (b) (RS)
)
LaTeX Font Info: Trying to load font information for T1+lmtt on input line 3
LaTeX Font Info: Trying to load font information for T1+lmtt on input line 4
1.
(D:\MikTex\tex/latex/lm\t1lmtt.fd
@@ -501,10 +510,10 @@ Package microtype Info: Loading generic protrusion settings for font family
(microtype) For optimal results, create family-specific settings.
(microtype) See the microtype manual for details.
LaTeX Font Info: External font `lmex10' loaded for size
(Font) <9> on input line 31.
(Font) <9> on input line 41.
LaTeX Font Info: External font `lmex10' loaded for size
(Font) <6> on input line 31.
LaTeX Font Info: Trying to load font information for TS1+lmr on input line 3
(Font) <6> on input line 41.
LaTeX Font Info: Trying to load font information for TS1+lmr on input line 4
6.
(D:\MikTex\tex/latex/lm\ts1lmr.fd
File: ts1lmr.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
@@ -513,80 +522,49 @@ File: ts1lmr.fd 2015/05/01 v1.6.1 Font defs for Latin Modern
{C:/Users/Markyan04/AppData/Local/MiKTeX/fonts/map/pdftex/pdftex.map}{D:/MikTex
/fonts/enc/dvips/lm/lm-ec.enc}{D:/MikTex/fonts/enc/dvips/lm/lm-rm.enc}{D:/MikTe
x/fonts/enc/dvips/lm/lm-mathit.enc}{D:/MikTex/fonts/enc/dvips/lm/lm-mathsy.enc}
{D:/MikTex/fonts/enc/dvips/lm/lm-ts1.enc}]
Underfull \vbox (badness 5105) has occurred while \output is active []
[2]
[3]
Underfull \vbox (badness 10000) has occurred while \output is active []
[4]
{D:/MikTex/fonts/enc/dvips/lm/lm-ts1.enc}] [2] [3] [4]
<fig-design-v4-from-user-svg-cropped.pdf, id=26, 616.3025pt x 172.645pt>
File: fig-design-v4-from-user-svg-cropped.pdf Graphic file (type pdf)
<use fig-design-v4-from-user-svg-cropped.pdf>
Package pdftex.def Info: fig-design-v4-from-user-svg-cropped.pdf used on input
line 71.
(pdftex.def) Requested size: 277.69987pt x 77.79225pt.
[5] [6 <./fig-design-v4-from-user-svg-cropped.pdf>] [7{D:/MikTex/fonts/enc/dvip
s/lm/lm-mathex.enc}]
Overfull \hbox (8.34737pt too wide) in paragraph at lines 137--139
\T1/lmr/m/n/10 Because dif-fu-sion op-ti-miza-tion can ex-hibit timestep im-bal
-ance (i.e., some timesteps
[]
[8] [9]
<typeclass-cropped.pdf, id=141, 616.3025pt x 221.82875pt>
line 81.
(pdftex.def) Requested size: 345.38622pt x 93.48433pt.
[5] [6 <./fig-design-v4-from-user-svg-cropped.pdf>] [7{D:/MikTex/fonts/enc/dvi
ps/lm/lm-mathex.enc}] [8]
[9]
<typeclass-cropped.pdf, id=143, 616.3025pt x 221.82875pt>
File: typeclass-cropped.pdf Graphic file (type pdf)
<use typeclass-cropped.pdf>
Package pdftex.def Info: typeclass-cropped.pdf used on input line 195.
Package pdftex.def Info: typeclass-cropped.pdf used on input line 205.
(pdftex.def) Requested size: 340.17958pt x 122.4462pt.
Underfull \vbox (badness 10000) has occurred while \output is active []
[10]
[11 <./typeclass-cropped.pdf>] [12]
<fig-benchmark-story-v2.png, id=172, 1089.6345pt x 360.036pt>
[10] [11 <./typeclass-cropped.pdf>] [12]
<fig-benchmark-story-v2.png, id=174, 1089.6345pt x 360.036pt>
File: fig-benchmark-story-v2.png Graphic file (type png)
<use fig-benchmark-story-v2.png>
Package pdftex.def Info: fig-benchmark-story-v2.png used on input line 225.
Package pdftex.def Info: fig-benchmark-story-v2.png used on input line 235.
(pdftex.def) Requested size: 347.12354pt x 114.69197pt.
Underfull \vbox (badness 10000) has occurred while \output is active []
[13 <./fig-benchmark-story-v2.png>]
<fig-benchmark-ablations-v1.png, id=179, 727.299pt x 328.5pt>
<fig-benchmark-ablations-v1.png, id=181, 727.299pt x 328.5pt>
File: fig-benchmark-ablations-v1.png Graphic file (type png)
<use fig-benchmark-ablations-v1.png>
Package pdftex.def Info: fig-benchmark-ablations-v1.png used on input line 278
Package pdftex.def Info: fig-benchmark-ablations-v1.png used on input line 288
.
(pdftex.def) Requested size: 347.12354pt x 156.78598pt.
[14] [15 <./fig-benchmark-ablations-v1.png>]
Overfull \hbox (5.31874pt too wide) in paragraph at lines 320--321
\T1/lmr/m/n/10 This pa-per ad-dresses the data scarcity and share-abil-ity bar-
ri-ers that limit machine-
[]
Overfull \hbox (2.54008pt too wide) in paragraph at lines 322--323
[]\T1/lmr/m/n/10 Overall, Mask-DDPM pro-vides a re-pro-ducible foun-da-tion for
gen-er-at-ing share-
[]
(main.bbl [16] [17] [18]) [19] (main.aux)
[14 <./fig-benchmark-ablations-v1.png>] [15] (main.bbl [16] [17] [18])
[19] (main.aux)
***********
LaTeX2e <2025-11-01>
L3 programming layer <2025-12-24>
***********
)
Here is how much of TeX's memory you used:
6340 strings out of 467871
97321 string characters out of 5435199
552249 words of memory out of 5000000
35104 multiletter control sequences out of 15000+600000
6672 strings out of 467871
103050 string characters out of 5435199
561035 words of memory out of 5000000
35432 multiletter control sequences out of 15000+600000
706871 words of font info for 99 fonts, out of 8000000 for 9000
1141 hyphenation exceptions out of 8191
57i,9n,65p,2477b,345s stack positions out of 10000i,1000n,20000p,200000b,200000s
57i,9n,65p,2477b,346s stack positions out of 10000i,1000n,20000p,200000b,200000s
<D:/MikTex/fonts/type1/public/lm/lmbx10.pfb><D:/MikTex/fonts/type1/public/lm/
lmbx12.pfb><D:/MikTex/fonts/type1/public/lm/lmbx9.pfb><D:/MikTex/fonts/type1/pu
blic/lm/lmex10.pfb><D:/MikTex/fonts/type1/public/lm/lmmi10.pfb><D:/MikTex/fonts
@@ -600,9 +578,9 @@ type1/public/lm/lmri9.pfb><D:/MikTex/fonts/type1/public/lm/lmsy10.pfb><D:/MikTe
x/fonts/type1/public/lm/lmsy7.pfb><D:/MikTex/fonts/type1/public/lm/lmsy9.pfb><D
:/MikTex/fonts/type1/public/lm/lmtt10.pfb><D:/MikTex/fonts/type1/public/lm/lmtt
9.pfb><D:/MikTex/fonts/type1/public/amsfonts/symbols/msbm10.pfb>
Output written on main.pdf (19 pages, 1109086 bytes).
Output written on main.pdf (19 pages, 1109663 bytes).
PDF statistics:
311 PDF objects out of 1000 (max. 8388607)
313 PDF objects out of 1000 (max. 8388607)
0 named destinations out of 1000 (max. 500000)
13845 words of extra memory for PDF output out of 14400 (max. 10000000)
13851 words of extra memory for PDF output out of 14400 (max. 10000000)

BIN
LaTeX2e+Proceedings+Templates+download/main.pdf
View File

Binary file not shown.

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}