1. Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
- Author
-
He, Hao, Zha, Kaiwen, and Katabi, Dina
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer Science - Cryptography and Security ,Artificial Intelligence (cs.AI) ,Computer Science - Artificial Intelligence ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,Cryptography and Security (cs.CR) ,Machine Learning (cs.LG) - Abstract
Indiscriminate data poisoning attacks are quite effective against supervised learning. However, not much is known about their impact on unsupervised contrastive learning (CL). This paper is the first to consider indiscriminate poisoning attacks of contrastive learning. We propose Contrastive Poisoning (CP), the first effective such attack on CL. We empirically show that Contrastive Poisoning, not only drastically reduces the performance of CL algorithms, but also attacks supervised learning models, making it the most generalizable indiscriminate poisoning attack. We also show that CL algorithms with a momentum encoder are more robust to indiscriminate poisoning, and propose a new countermeasure based on matrix completion. Code is available at: https://github.com/kaiwenzha/contrastive-poisoning., Comment: ICLR 2023 Spotlight (notable top 25%). The first two authors contributed equally to this paper
- Published
- 2022
- Full Text
- View/download PDF