Towards Adversarially Robust Continual Learning
This addresses the security of continual learning models in real-world applications, which is an incremental step as it extends adversarial robustness research to a new context.
The paper tackles the problem of adversarial vulnerability in continual learning models, proposing a novel method called TABA that boosts robustness, with experiments on CIFAR-10 and CIFAR-100 showing efficacy in defending against attacks.
Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real world. Deep learning models, however, are shown to be vulnerable to adversarial attacks. Though there are many studies on the model robustness in the context of standard supervised learning, protecting continual learning from adversarial attacks has not yet been investigated. To fill in this research gap, we are the first to study adversarial robustness in continual learning and propose a novel method called \textbf{T}ask-\textbf{A}ware \textbf{B}oundary \textbf{A}ugmentation (TABA) to boost the robustness of continual learning models. With extensive experiments on CIFAR-10 and CIFAR-100, we show the efficacy of adversarial training and TABA in defending adversarial attacks.