SoK: Pitfalls in Evaluating Black-Box Attacks

arXiv:2310.17534v2 Announce Type: replace-cross
Abstract: Numerous works study black-box attacks on image classifiers. However, these works make different assumptions on the adversary's knowledge and current literature lacks a cohesive organization centered around the threat model. To systematize knowledge in this area, we propose a taxonomy over the threat space spanning the axes of feedback granularity, the access of interactive queries, and the quality and quantity of the auxiliary data available to the attacker. Our new taxonomy provides three key insights. …

abstract arxiv assumptions attacks box classifiers cs.ai cs.cr cs.cv cs.lg current feedback image knowledge literature organization space study taxonomy threat type