Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

arXiv:2404.12120v1 Announce Type: new
Abstract: This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack is one where the attacker is aware of the defenses and adapts their strategy accordingly. Our proposed method leverages adversarial training to reinforce the ability to detect attacks, without compromising clean accuracy. During the training phase, we integrate into the dataset adversarial examples, which were optimized to …

abstract adversarial arxiv attacks classifier cs.ai cs.cv detection detectors paper performance radar resilient retraining robust robustness strategy the guardian type via