AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

arXiv:2404.19460v1 Announce Type: cross
Abstract: Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using different experimental setups, hyperparameter settings, and number of forward and backward calls to the target models. This provides overly-optimistic and even biased evaluations that may unfairly favor one particular attack over the others. In this work, we aim to overcome these limitations by proposing AttackBench, i.e., the first evaluation framework that enables a …

adversarial arxiv attacks cs.cr cs.cv cs.lg examples forward may novel settings target