论文标题
对无监督对比学习的不加区分危害中毒攻击
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
论文作者
论文摘要
不加选择的数据中毒攻击非常有效地抵抗监督学习。但是，对于它们对无监督对比学习（CL）的影响尚不了解。本文是第一个考虑对比度学习的不加选择的中毒攻击的文章。我们提出了对比中毒（CP），这是对CL的第一次有效攻击。我们从经验上表明，对比中毒，不仅大大降低了CL算法的性能，而且还攻击了监督的学习模型，使其成为最不可分割的中毒攻击。我们还表明，具有动量编码器的CL算法对于不加选择的中毒更强大，并提出了基于矩阵完成的新对策。代码可在以下网址获得：https：//github.com/kaiwenzha/contrastive-poisoning。
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.
