Towards Query-Efficient Decision-Based Adversarial Attacks Through Frequency Domain

Jianhao Fu, Xiang Ling, Yaguan Qian, Changjiang Li, Tianyue Luo, Jingzheng Wu

Abstract: Deep neural networks are vulnerable to adversarial examples, where decision-based attacks can generate adversarial examples based solely on the predicted labels. However, these attacks typically require excessive queries to attack one example. Considering this challenge, we propose FBA (Frequency based Boundary Attack), a decision-based attack against the limitation of query efficiency. FBA incorporates a novel search process, utilizing high-frequency based importance sampling for efficient gradient estimation. Empirical results confirm the superior query efficiency of our method. Specifically, FBA surpasses SOTA attacks by achieving a 54% average improvement in query efficiency, quantified by the reduction in perturbation size within the same number of queries.