论文标题
LeThean Attack：在线数据中毒技术
Lethean Attack: An Online Data Poisoning Technique
论文作者
论文摘要
数据中毒是一种对抗性情况，攻击者将特殊精心制作的样本序列馈送到在线模型中以颠覆学习。我们引入了LeThean Attack，这是一种新型的数据中毒技术，可引起在线模型上的灾难性遗忘。我们在测试时间培训的背景下应用了攻击，这是一个现代的在线学习框架，旨在进行分配变化的概括。我们介绍了理论原理，并从经验上将其与自然诱发遗忘的其他样本序列进行了比较。我们的结果表明，使用LeThean攻击，对手可以使用短样本序列将测试时间训练模型恢复为弹翼精度性能。
Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique that induces catastrophic forgetting on an online model. We apply the attack in the context of Test-Time Training, a modern online learning framework aimed for generalization under distribution shifts. We present the theoretical rationale and empirically compare it against other sample sequences that naturally induce forgetting. Our results demonstrate that using lethean attacks, an adversary could revert a test-time training model back to coin-flip accuracy performance using a short sample sequence.
