BrainWash：一种在持续学习中引发遗忘的投毒攻击
BrainWash: A Poisoning Attack to Forget in Continual Learning
AI总结：
本文提出了一种名为BrainWash的新型数据投毒攻击方法，仅需模型当前参数和最新任务数据即可诱发持续学习模型对先前任务的灾难性遗忘。
摘要：
持续学习在深度学习社区中获得了广泛关注，为序列学习这一难题提供了有前景的解决方案。然而，这一范式的一个很大程度上未被探索的方面是其对对抗性攻击的易感性，尤其是以诱发遗忘为目的的攻击。在本文中，我们引入了“BrainWash”，一种旨在对持续学习器施加遗忘的新型数据投毒方法。通过将BrainWash噪声添加到各种基线中，我们证明了即使使用这些持续学习基线，训练好的持续学习器也会被诱发灾难性地遗忘其先前学习的任务。我们方法的一个重要特征是，攻击者无需访问先前任务的数据，仅凭借模型当前的参数和属于最新任务的数据即可实施攻击。我们广泛的实验突出了BrainWash的有效性，展示了在各种基于正则化的持续学习方法中性能的下降。
英文摘要：
Continual learning has gained substantial attention within the deep learning community, offering promising solutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its susceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce "BrainWash," a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the BrainWash noise to a variety of baselines, we demonstrate how a trained continual learner can be induced to forget its previously learned tasks catastrophically, even when using these continual learning baselines. An important feature of our approach is that the attacker requires no access to previous tasks' data and is armed merely with the model's current parameters and the data belonging to the most recent task. Our extensive experiments highlight the efficacy of BrainWash, showcasing degradation in performance across various regularization-based continual learning methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
