Transferability Ranking of Adversarial Examples

arXiv:2208.10878v2 Announce Type: replace
Abstract: Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target model. Until now, the prevalent method to ascertain success has been trial and error-testing crafted samples directly on the victim model. This approach, however, risks detection with every attempt, forcing attackers to either perfect their first try or face exposure. Our paper introduces a …

abstract adversarial adversarial examples arxiv box challenge craft cs.cr cs.lg error examples ranking samples success testing type unique will