Siyuan Cheng (Purdue University), Guanhong Tao (Purdue University), Yingqi Liu (Purdue University), Shengwei An (Purdue University), Xiangzhe Xu (Purdue University), Shiwei Feng (Purdue University), Guangyu Shen (Purdue University), Kaiyuan Zhang (Purdue University), Qiuling Xu (Purdue University), Shiqing Ma (Rutgers University), Xiangyu Zhang (Purdue University)

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.

View More Papers

Accountable Javascript Code Delivery

Ilkan Esiyok (CISPA Helmholtz Center for Information Security), Pascal Berrang (University of Birmingham & Nimiq), Katriel Cohn-Gordon (Meta), Robert Künnemann (CISPA Helmholtz Center for Information Security)

Read More

CHKPLUG: Checking GDPR Compliance of WordPress Plugins via Cross-language...

Faysal Hossain Shezan (University of Virginia), Zihao Su (University of Virginia), Mingqing Kang (Johns Hopkins University), Nicholas Phair (University of Virginia), Patrick William Thomas (University of Virginia), Michelangelo van Dam (in2it), Yinzhi Cao (Johns Hopkins University), Yuan Tian (UCLA)

Read More

RoVISQ: Reduction of Video Service Quality via Adversarial Attacks...

Jung-Woo Chang (University of California San Diego), Mojan Javaheripi (University of California San Diego), Seira Hidano (KDDI Research, Inc.), Farinaz Koushanfar (University of California San Diego)

Read More

AuthentiSense: A Scalable Behavioral Biometrics Authentication Scheme using Few-Shot...

Hossein Fereidooni (Technical University of Darmstadt), Jan Koenig (University of Wuerzburg), Phillip Rieger (Technical University of Darmstadt), Marco Chilese (Technical University of Darmstadt), Bora Goekbakan (KOBIL, Germany), Moritz Finke (University of Wuerzburg), Alexandra Dmitrienko (University of Wuerzburg), Ahmad-Reza Sadeghi (Technical University of Darmstadt)

Read More