부산대학교 도서관

Most current classifiers are vulnerable to adversarial examples, small input perturbations that change the classification output. Many existing attack algorithms cover various settings, from white-box to black-box classifiers, but typically assume that the answers are deterministic and often fail when they are not. We therefore propose a new adversarial decision-based attack specifically designed for classifiers with probabilistic outputs. It is based on the HopSkipJump attack by Chen et al. (2019, arXiv:1904.02144v5 ), a strong and query efficient decision-based attack originally designed for deterministic classifiers. Our P(robabilisticH)opSkipJump attack adapts its amount of queries to maintain HopSkipJump's original output quality across various noise levels, while converging to its query efficiency as the noise level decreases. We test our attack on various noise models, including state-of-the-art off-the-shelf randomized defenses, and show that they offer almost no extra robustness to decision-based attacks. Code is available at https://github.com/cjsg/PopSkipJump .
Comment: ICML'21. Code available at https://github.com/cjsg/PopSkipJump . 9 pages & 7 figures in main part, 14 pages & 10 figures in appendix