Changjiang Li, Stony Brook University; Ren Pang, Bochuan Cao, Zhaohan Xi, and Jinghui Chen, Pennsylvania State University; Shouling Ji, Zhejiang University; Ting Wang, Stony Brook University
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models, only to be activated by specific triggers. However, thus far it remains under-explored how contrastive backdoor attacks fundamentally differ from their supervised counterparts, which impedes the development of effective defenses against the emerging threat.
This work represents a solid step toward answering this critical question. Specifically, we define TRL, a unified framework that encompasses both supervised and contrastive backdoor attacks. Through the lens of TRL, we uncover that the two types of attacks operate through distinctive mechanisms: in supervised attacks, the learning of benign and backdoor tasks tends to occur independently, while in contrastive attacks, the two tasks are deeply intertwined both in their representations and throughout their learning processes. This distinction leads to the disparate learning dynamics and feature distributions of supervised and contrastive attacks. More importantly, we reveal that the specificities of contrastive backdoor attacks entail important implications from a defense perspective: existing defenses for supervised attacks are often inadequate and not easily retrofitted to contrastive attacks. We also explore several promising alternative defenses and discuss their potential challenges. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks, pointing to promising directions for future research.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Changjiang Li and Ren Pang and Bochuan Cao and Zhaohan Xi and Jinghui Chen and Shouling Ji and Ting Wang},
title = {On the Difficulty of Defending Contrastive Learning against Backdoor Attacks},
booktitle = {33rd USENIX Security Symposium (USENIX Security 24)},
year = {2024},
isbn = {978-1-939133-44-1},
address = {Philadelphia, PA},
pages = {2901--2918},
url = {https://www.usenix.org/conference/usenixsecurity24/presentation/li-changjiang},
publisher = {USENIX Association},
month = aug
}