BrainWash: A Poisoning Attack to Forget in Continual Learning

Ali Abbasi, Parsa Nooralinejad, Hamed Pirsiavash, Soheil Kolouri

Abstract: Continual learning has gained substantial attention within the deep learning community, offering promising so- lutions to the challenging problem of sequential learning. Yet, a largely unexplored facet of this paradigm is its sus- ceptibility to adversarial attacks, especially with the aim of inducing forgetting. In this paper, we introduce “Brain- Wash,” a novel data poisoning method tailored to impose forgetting on a continual learner. By adding the Brain- Wash 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 us- ing these continual learning baselines. An important fea- ture of our approach is that the attacker requires no ac- cess 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 perfor- mance across various regularization and memory replay- based continual learning methods. Our code is available here: https://github.com/mint-vu/Brainwash