BounceAttack: A Query-Efficient Decision-based Adversarial Attack by Bouncing into the Wild
Jie Wan, Jianhao Fu, Lijin Wang, Ziqi Yang
IEEE Symposium on Security and Privacy 2024 · Day 1 · Continental Ballroom 5
In the rapidly evolving landscape of artificial intelligence, the robustness of machine learning models against adversarial attacks remains a critical concern. The talk "BounceAttack: A Query-Efficient Decision-based Adversarial Attack by Bouncing into the Wild," presented by Jie Wan from Zhejiang University, introduces a novel and highly effective method for generating **adversarial examples** in a **black-box setting**. This research focuses on traditional classification models, demonstrating how imperceptible perturbations can be added to legitimate inputs, causing a classifier to mispredict without altering human recognition of the original content.
AI review
This talk introduces BounceAttack, a highly query-efficient decision-based black-box adversarial attack leveraging a novel "Bounce Decomposition" for gradient estimation. It significantly outperforms prior methods like HSJA in generating imperceptible perturbations, posing a critical challenge to current AI model defenses. This research offers crucial insights for both understanding vulnerabilities and developing more robust machine learning models.