Preprint Open access
GuidedRay: Diversity-Guided Direction Discovery for Targeted Hard-Label Black-Box Attacks
Deep neural networks are vulnerable to adversarial attacks. Among black-box attacks, targeted decision-based attacks are particularly difficult: the attacker observes only the target model's top-1 label and aims to make it predict a prespecified target class under a bounded perturbation. Before perturbation refinement, …