Papers › Data Poisoning based Backdoor Attacks to Contrastive Learning
Data Poisoning based Backdoor Attacks to Contrastive Learning
Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong
Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs) in which an attacker injects poisoned inputs into the pre-training dataset so the encoder is backdoored. However existing DPBAs achieve limited effectiveness. In this work we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL. CorruptEncoder introduces a new attack strategy to create poisoned inputs and uses a theory-guided method to maximize attack effectiveness. Our experiments show that CorruptEncoder substantially outperforms existing DPBAs. In particular CorruptEncoder is the first DPBA that achieves more than 90% attack success rates with only a few (3) reference images and a small poisoning ratio (0.5%). Moreover we also propose a defense called localized cropping to defend against DPBAs. Our results show that our defense can reduce the effectiveness of DPBAs but it sacrifices the utility of the encoder highlighting the need for new defenses.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections