2023-03-10 更新
Decision-BADGE: Decision-based Adversarial Batch Attack with Directional Gradient Estimation
Authors:Geunhyeok Yu, Minwoo Jeon, Hyoseok Hwang
The vulnerability of deep neural networks to adversarial examples has led to the rise in the use of adversarial attacks. While various decision-based and universal attack methods have been proposed, none have attempted to create a decision-based universal adversarial attack. This research proposes Decision-BADGE, which uses random gradient-free optimization and batch attack to generate universal adversarial perturbations for decision-based attacks. Multiple adversarial examples are combined to optimize a single universal perturbation, and the accuracy metric is reformulated into a continuous Hamming distance form. The effectiveness of accuracy metric as a loss function is demonstrated and mathematically proven. The combination of Decision-BADGE and the accuracy loss function performs better than both score-based image-dependent attack and white-box universal attack methods in terms of attack time efficiency. The research also shows that Decision-BADGE can successfully deceive unseen victims and accurately target specific classes.
PDF 10 pages (8 pages except for references), 6 figures, 6 tables
点此查看论文截图
