Optimization to the Rescue: Evading Binary Code Stylometry with Adversarial Use of Code Optimizations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Recent work suggests that it may be possible to determine the author of a binary program simply by analyzing stylistic features preserved within it. As this poses a threat to the privacy of programmers who wish to distribute their work anonymously, we consider steps that can be taken to mislead such analysis. We begin by exploring the effect of compiler optimizations on the features used for stylistic analysis. Building on these findings, we propose a gray-box attack on a state-of-the-art classifier using compiler optimizations. Finally, we discuss our results, as well as implications for the field of binary stylometry.

Original languageEnglish (US)
Title of host publicationCheckMate 2021 - Proceedings of the 2021 Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks, co-located with CCS 2021
PublisherAssociation for Computing Machinery, Inc
Pages1-10
Number of pages10
ISBN (Electronic)9781450385527
DOIs
StatePublished - Nov 19 2021
Event2021 Workshop on Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks, CheckMate 2021 - Virtual, Online, Korea, Republic of
Duration: Nov 19 2021 → …

Publication series

NameCheckMate 2021 - Proceedings of the 2021 Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks, co-located with CCS 2021

Conference

Conference2021 Workshop on Research on Offensive and Defensive Techniques in the Context of Man At The End (MATE) Attacks, CheckMate 2021
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period11/19/21 → …

Keywords

  • Adversarial machine learning
  • Bayesian optimization
  • Privacy
  • Stylometry

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'Optimization to the Rescue: Evading Binary Code Stylometry with Adversarial Use of Code Optimizations'. Together they form a unique fingerprint.

Cite this