AI RESEARCH
Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks
arXiv CS.LG
•
ArXi:2605.25663v1 Announce Type: new Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the feature space without committing to a specific adversarial class, wasting queries on diffuse, undirected progress. We We validate OTS on three score-based attacks (SimBA, Square Attack with cross-entropy loss, and Bandits) across five standard ImageNet classifiers (4,500 runs