Backdoor Contrastive Learning via Bi-level Trigger Optimization

arXiv:2404.07863v1 Announce Type: new
Abstract: Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor could be misled to embed backdoored data close to an attack target class, thus fooling the downstream predictor to misclassify it as the target. Existing attacks usually adopt a fixed trigger pattern and poison the training set with trigger-injected data, hoping for the feature …

arxiv backdoor cs.cr optimization trigger