JTrans: Jump-aware transformer for binary code similarity detection

Hao Wang, Wenjie Qu, Gilad Katz, Wenyu Zhu, Zeyu Gao, Han Qiu, Jianwei Zhuge, Chao Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Binary code similarity detection (BCSD) has important applications in various fields such as vulnerabilities detection, software component analysis, and reverse engineering. Recent studies have shown that deep neural networks (DNNs) can comprehend instructions or control-flow graphs (CFG) of binary code and support BCSD. In this study, we propose a novel Transformer-based approach, namely jTrans, to learn representations of binary code. It is the first solution that embeds control flow information of binary code into Transformer-based language models, by using a novel jump-aware representation of the analyzed binaries and a newly-designed pre-training task. Additionally, we release to the community a newly-created large dataset of binaries, BinaryCorp, which is the most diverse to date. Evaluation results show that jTrans outperforms state-of-the-art (SOTA) approaches on this more challenging dataset by 30.5% (i.e., from 32.0% to 62.5%). In a real-world task of known vulnerability searching, jTrans achieves a recall that is 2X higher than existing SOTA baselines.

Original languageEnglish
Title of host publicationISSTA 2022 - Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis
EditorsSukyoung Ryu, Yannis Smaragdakis
PublisherAssociation for Computing Machinery, Inc
Pages1-13
Number of pages13
ISBN (Electronic)9781450393799
DOIs
StatePublished - 18 Jul 2022
Event31st ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2022 - Virtual, Online, Korea, Republic of
Duration: 18 Jul 202222 Jul 2022

Publication series

NameISSTA 2022 - Proceedings of the 31st ACM SIGSOFT International Symposium on Software Testing and Analysis

Conference

Conference31st ACM SIGSOFT International Symposium on Software Testing and Analysis, ISSTA 2022
Country/TerritoryKorea, Republic of
CityVirtual, Online
Period18/07/2222/07/22

Keywords

  • Binary Analysis
  • Datasets
  • Neural Networks
  • Similarity Detection

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Fingerprint

Dive into the research topics of 'JTrans: Jump-aware transformer for binary code similarity detection'. Together they form a unique fingerprint.

Cite this