Defending Against Repetitive Backdoor Attacks on Semi-Supervised Learning Through Lens of Rate-Distortion-Perception Trade-Off
Part Of
Proceedings - 2025 IEEE Winter Conference on Applications of Computer Vision, WACV 2025
Start Page
6465
End Page
6474
ISBN
[9798331510831]
Date Issued
2025-02-26
Author(s)
Abstract
Semi-supervised learning (SSL) has achieved remarkable performance with a small fraction of labeled data by leveraging vast amounts of unlabeled data from the Internet. However, this large pool of untrusted data is extremely vulnerable to data poisoning, leading to potential backdoor attacks. Current backdoor defenses are not yet effective against such a vulnerability in SSL. In this study, we propose a novel method, Unlabeled Data Purification (UPure), to disrupt the association between trigger patterns and target classes by introducing perturbations in the frequency domain. By leveraging the Rate-Distortion-Perception (RDP) trade-off, we further identify the frequency band, where the perturbations are added, and Justify this selection. Notably, UPure purifies poisoned unlabeled data without the need of extra clean labeled data. Extensive experiments on four benchmark datasets and five SSL algorithms demonstrate that UPure effectively reduces the attack success rate from 99.78% to 0% while maintaining model accuracy. Code is available here: https://github.com/chengyi-chris/UPure.
Event(s)
2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV
SDGs
Publisher
IEEE
Type
conference paper