DIFT: Protecting Contrastive Learning Against Data Poisoning Backdoor Attacks
Jiang Zhu, Yulin Jin, Qingqing Ye, Zhibiao Guo, Kun Fang, Ruochen Du, Yingnan Zhao, Haibo Hu
Abstract
Contrastive learning (CL) is a popular learning paradigm that excels in extracting meaningful representations from unlabeled data. Recent studies have shown that CL is highly vulnerable to backdoor attacks. Current defenses against backdoor attacks in CL are primarily reactive and post-training. That is, the detection and elimination of backdoors are executed in the deployment phase of a given well-trained model. However, these post-training defenses are usually prone to degrading model utility and resource-intensive, causing that the backdoor detection and elimination from a fully-trained model is quite challenging. To address this issue, we argue for a fundamental perspective, i.e., integrating the defense into the model
BibTeX
@inproceedings{aaai2026_diftprotectingco,
title = {DIFT: Protecting Contrastive Learning Against Data Poisoning Backdoor Attacks},
author = {Jiang Zhu and Yulin Jin and Qingqing Ye and Zhibiao Guo and Kun Fang and Ruochen Du and Yingnan Zhao and Haibo Hu},
booktitle = {AAAI 2026},
year = {2026}
}