PopSkipJump: Decision-Based Attack for Probabilistic Classifiers

Author name not available (Why is that?)

Publication date: 14 June 2021

Abstract: 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 .

Has companion code repository: https://github.com/cjsg/PopSkipJump

This page was built for publication: PopSkipJump: Decision-Based Attack for Probabilistic Classifiers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6370243)