forked from manbo/internal-docs
165 lines
9.2 KiB
TeX
165 lines
9.2 KiB
TeX
\relax
|
|
\citation{10.1007/s10844-022-00753-1,Nankya2023-gp}
|
|
\@writefile{toc}{\contentsline {title}{Mask-DDPM: Transformer-Conditioned Mixed-Type Diffusion for Semantically Valid ICS Telemetry Synthesis}{1}{}\protected@file@percent }
|
|
\@writefile{toc}{\authcount {4}}
|
|
\@writefile{toc}{\contentsline {author}{Zhenglan Chen \and Mingzhe Yang \and Hongyu Yan \and Huan Yang}{1}{}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {1}Introduction}{1}{}\protected@file@percent }
|
|
\newlabel{sec:intro}{{1}{1}{}{section.1}{}}
|
|
\citation{shin}
|
|
\citation{info16100910}
|
|
\citation{pmlr-v202-kotelnikov23a,rasul2021autoregressivedenoisingdiffusionmodels}
|
|
\citation{jiang2023netdiffusionnetworkdataaugmentation}
|
|
\citation{pmlr-v202-kotelnikov23a}
|
|
\citation{10.1145/1151659.1159928}
|
|
\citation{Ring_2019}
|
|
\citation{10.1145/3544216.3544251}
|
|
\citation{Lin_2020}
|
|
\citation{7469060,10.1145/3055366.3055375}
|
|
\citation{NEURIPS2020_4c5bcfec}
|
|
\citation{song2021scorebasedgenerativemodelingstochastic}
|
|
\citation{rasul2021autoregressivedenoisingdiffusionmodels}
|
|
\citation{tashiro2021csdiconditionalscorebaseddiffusion}
|
|
\citation{wen2024diffstgprobabilisticspatiotemporalgraph}
|
|
\citation{liu2023pristiconditionaldiffusionframework}
|
|
\citation{kong2021diffwaveversatilediffusionmodel}
|
|
\citation{11087622}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {2}Related Work}{3}{}\protected@file@percent }
|
|
\newlabel{sec:related}{{2}{3}{}{section.2}{}}
|
|
\citation{austin2023structureddenoisingdiffusionmodels}
|
|
\citation{Lin_2020}
|
|
\citation{hoogeboom2021argmaxflowsmultinomialdiffusion}
|
|
\citation{li2022diffusionlmimprovescontrollabletext}
|
|
\citation{meng2025aflnetyearslatercoverageguided,godefroid2017learnfuzzmachinelearninginput,she2019neuzzefficientfuzzingneural}
|
|
\citation{dai2019transformerxlattentivelanguagemodels}
|
|
\citation{zhou2021informerefficienttransformerlong}
|
|
\citation{wu2022autoformerdecompositiontransformersautocorrelation}
|
|
\citation{zhou2022fedformerfrequencyenhanceddecomposed}
|
|
\citation{nie2023patchtst}
|
|
\citation{rasul2021autoregressivedenoisingdiffusionmodels,tashiro2021csdiconditionalscorebaseddiffusion,wen2024diffstgprobabilisticspatiotemporalgraph,liu2023pristiconditionaldiffusionframework,kong2021diffwaveversatilediffusionmodel,11087622}
|
|
\citation{nist2023sp80082}
|
|
\citation{ho2020denoising,song2021score}
|
|
\citation{kollovieh2023tsdiff,sikder2023transfusion}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {3}Methodology}{5}{}\protected@file@percent }
|
|
\newlabel{sec:method}{{3}{5}{}{section.3}{}}
|
|
\citation{vaswani2017attention}
|
|
\citation{ho2020denoising,kollovieh2023tsdiff}
|
|
\citation{austin2021structured,shi2024simplified}
|
|
\citation{yuan2025ctu,sha2026ddpm}
|
|
\citation{vaswani2017attention}
|
|
\citation{vaswani2017attention,nist2023sp80082}
|
|
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces Masked-DDPM: Unified Synthesis for ICS traffic}}{6}{}\protected@file@percent }
|
|
\newlabel{fig:design}{{1}{6}{}{figure.1}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Transformer trend module for continuous dynamics}{6}{}\protected@file@percent }
|
|
\newlabel{sec:method-trans}{{3.1}{6}{}{subsection.3.1}{}}
|
|
\citation{kollovieh2023tsdiff,sikder2023transfusion}
|
|
\citation{vaswani2017attention,kollovieh2023tsdiff,yuan2025ctu}
|
|
\citation{ho2020denoising}
|
|
\citation{ho2020denoising,song2021score}
|
|
\citation{kollovieh2023tsdiff,sikder2023transfusion}
|
|
\newlabel{eq:additive_decomp}{{1}{7}{}{equation.1}{}}
|
|
\newlabel{eq:trend_prediction}{{2}{7}{}{equation.2}{}}
|
|
\newlabel{eq:trend_loss}{{3}{7}{}{equation.3}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}DDPM for continuous residual generation}{7}{}\protected@file@percent }
|
|
\newlabel{sec:method-ddpm}{{3.2}{7}{}{subsection.3.2}{}}
|
|
\citation{ho2020denoising,sikder2023transfusion}
|
|
\citation{hang2023efficient}
|
|
\citation{yuan2025ctu,sha2026ddpm}
|
|
\citation{austin2021structured,shi2024simplified}
|
|
\citation{nist2023sp80082}
|
|
\citation{shi2024simplified}
|
|
\newlabel{eq:forward_corruption}{{4}{8}{}{equation.4}{}}
|
|
\newlabel{eq:forward_corruption_eq}{{5}{8}{}{equation.5}{}}
|
|
\newlabel{eq:reverse_process}{{6}{8}{}{equation.6}{}}
|
|
\newlabel{eq:ddpm_loss}{{7}{8}{}{equation.7}{}}
|
|
\newlabel{eq:snr_loss}{{8}{8}{}{equation.8}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}Masked diffusion for discrete ICS variables}{8}{}\protected@file@percent }
|
|
\newlabel{sec:method-discrete}{{3.3}{8}{}{subsection.3.3}{}}
|
|
\citation{nist2023sp80082}
|
|
\citation{shi2024simplified,yuan2025ctu}
|
|
\citation{nist2023sp80082}
|
|
\newlabel{eq:masking_process}{{9}{9}{}{equation.9}{}}
|
|
\newlabel{eq:discrete_denoising}{{10}{9}{}{equation.10}{}}
|
|
\newlabel{eq:discrete_loss}{{11}{9}{}{equation.11}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.4}Type-aware decomposition as factorization and routing layer}{9}{}\protected@file@percent }
|
|
\newlabel{sec:method-types}{{3.4}{9}{}{subsection.3.4}{}}
|
|
\citation{shi2025tabdiff,yuan2025ctu,nist2023sp80082}
|
|
\citation{kollovieh2023tsdiff,sikder2023transfusion}
|
|
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces Type assignment and six-type taxonomy.}}{11}{}\protected@file@percent }
|
|
\newlabel{fig:type_taxonomy}{{2}{11}{}{figure.2}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.5}Joint optimization and end-to-end sampling}{11}{}\protected@file@percent }
|
|
\newlabel{sec:method-joint}{{3.5}{11}{}{subsection.3.5}{}}
|
|
\citation{ho2020denoising,shi2024simplified,yuan2025ctu,nist2023sp80082}
|
|
\citation{coletta2023constrained,yang2001interlock,stenger2024survey}
|
|
\citation{lin1991divergence,yoon2019timegan}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {4}Benchmark}{12}{}\protected@file@percent }
|
|
\newlabel{sec:benchmark}{{4}{12}{}{section.4}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {4.1}Core fidelity, legality, and reproducibility}{12}{}\protected@file@percent }
|
|
\newlabel{sec:benchmark-quant}{{4.1}{12}{}{subsection.4.1}{}}
|
|
\@writefile{lof}{\contentsline {figure}{\numberline {3}{\ignorespaces Benchmark evidence chain.}}{13}{}\protected@file@percent }
|
|
\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{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{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}{}}
|
|
\bibstyle{splncs04}
|
|
\bibdata{references}
|
|
\bibcite{10.1145/3055366.3055375}{1}
|
|
\bibcite{info16100910}{2}
|
|
\bibcite{austin2023structureddenoisingdiffusionmodels}{3}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {5}Conclusion and Future Work}{16}{}\protected@file@percent }
|
|
\newlabel{sec:conclusion}{{5}{16}{}{section.5}{}}
|
|
\bibcite{austin2021structured}{4}
|
|
\bibcite{coletta2023constrained}{5}
|
|
\bibcite{dai2019transformerxlattentivelanguagemodels}{6}
|
|
\bibcite{godefroid2017learnfuzzmachinelearninginput}{7}
|
|
\bibcite{hang2023efficient}{8}
|
|
\bibcite{NEURIPS2020_4c5bcfec}{9}
|
|
\bibcite{ho2020denoising}{10}
|
|
\bibcite{hoogeboom2021argmaxflowsmultinomialdiffusion}{11}
|
|
\bibcite{jiang2023netdiffusionnetworkdataaugmentation}{12}
|
|
\bibcite{10.1007/s10844-022-00753-1}{13}
|
|
\bibcite{kollovieh2023tsdiff}{14}
|
|
\bibcite{kong2021diffwaveversatilediffusionmodel}{15}
|
|
\bibcite{pmlr-v202-kotelnikov23a}{16}
|
|
\bibcite{li2022diffusionlmimprovescontrollabletext}{17}
|
|
\bibcite{lin1991divergence}{18}
|
|
\bibcite{Lin_2020}{19}
|
|
\bibcite{liu2023pristiconditionaldiffusionframework}{20}
|
|
\bibcite{11087622}{21}
|
|
\bibcite{7469060}{22}
|
|
\bibcite{meng2025aflnetyearslatercoverageguided}{23}
|
|
\bibcite{Nankya2023-gp}{24}
|
|
\bibcite{nist2023sp80082}{25}
|
|
\bibcite{nie2023patchtst}{26}
|
|
\bibcite{rasul2021autoregressivedenoisingdiffusionmodels}{27}
|
|
\bibcite{Ring_2019}{28}
|
|
\bibcite{sha2026ddpm}{29}
|
|
\bibcite{she2019neuzzefficientfuzzingneural}{30}
|
|
\bibcite{shi2024simplified}{31}
|
|
\bibcite{shi2025tabdiff}{32}
|
|
\bibcite{shin}{33}
|
|
\bibcite{sikder2023transfusion}{34}
|
|
\bibcite{song2021scorebasedgenerativemodelingstochastic}{35}
|
|
\bibcite{song2021score}{36}
|
|
\bibcite{stenger2024survey}{37}
|
|
\bibcite{tashiro2021csdiconditionalscorebaseddiffusion}{38}
|
|
\bibcite{vaswani2017attention}{39}
|
|
\bibcite{10.1145/1151659.1159928}{40}
|
|
\bibcite{wen2024diffstgprobabilisticspatiotemporalgraph}{41}
|
|
\bibcite{wu2022autoformerdecompositiontransformersautocorrelation}{42}
|
|
\bibcite{yang2001interlock}{43}
|
|
\bibcite{10.1145/3544216.3544251}{44}
|
|
\bibcite{yoon2019timegan}{45}
|
|
\bibcite{yuan2025ctu}{46}
|
|
\bibcite{zhou2021informerefficienttransformerlong}{47}
|
|
\bibcite{zhou2022fedformerfrequencyenhanceddecomposed}{48}
|
|
\gdef \@abspage@last{21}
|