CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning

arXiv:2211.08229v5 Announce Type: replace
Abstract: 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 …

arxiv attacker attacks backdoor backdoor attacks cs.cr cs.cv cs.lg data data poisoning dataset general image images inputs poisoning purpose text training trains vulnerable