BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense

4Citations
Citations of this article
12Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

Cheng, S., Tao, G., Liu, Y., An, S., Xu, X., Feng, S., … Zhang, X. (2023). BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense. In 30th Annual Network and Distributed System Security Symposium, NDSS 2023. The Internet Society. https://doi.org/10.14722/ndss.2023.24944

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free