Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

arXiv:2404.00540v1 Announce Type: new
Abstract: The vulnerability of deep neural networks to adversarial patches has motivated numerous defense strategies for boosting model robustness. However, the prevailing defenses depend on single observation or pre-established adversary information to counter adversarial patches, often failing to be confronted with unseen or adaptive adversarial attacks and easily exhibiting unsatisfying performance in dynamic 3D environments. Inspired by active human perception and recurrent feedback mechanisms, we develop Embodied Active Defense (EAD), a proactive defensive strategy that actively …

abstract adversarial adversarial attacks arxiv attacks boosting cs.ai cs.cv defense embodied feedback however information model robustness networks neural networks observation robustness strategies type vulnerability