English

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

Cryptography and Security 2023-01-18 v1 Machine Learning

Abstract

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper, we propose a novel model backdoor forensics technique. Given a few attack samples such as inputs with backdoor triggers, which may represent different types of backdoors, our technique automatically decomposes them to clean inputs and the corresponding triggers. It then clusters the triggers based on their properties to allow automatic attack categorization and summarization. Backdoor scanners can then be automatically synthesized to find other instances of the same type of backdoor in other models. Our evaluation on 2,532 pre-trained models, 10 popular attacks, and comparison with 9 baselines show that our technique is highly effective. The decomposed clean inputs and triggers closely resemble the ground truth. The synthesized scanners substantially outperform the vanilla versions of existing scanners that can hardly generalize to different kinds of attacks.

Keywords

Cite

@article{arxiv.2301.06241,
  title  = {BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense},
  author = {Siyuan Cheng and Guanhong Tao and Yingqi Liu and Shengwei An and Xiangzhe Xu and Shiwei Feng and Guangyu Shen and Kaiyuan Zhang and Qiuling Xu and Shiqing Ma and Xiangyu Zhang},
  journal= {arXiv preprint arXiv:2301.06241},
  year   = {2023}
}
R2 v1 2026-06-28T08:12:16.198Z