Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning

arxiv(2022)

引用 0|浏览43
暂无评分
摘要
The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine learning models on the one hand and finding targeted defenses on the other. However, most of the adversarial attacks today leverage the gradient or logit information from the models to generate adversarial perturbation. Works in the more realistic domain: decision-based attacks, which generate adversarial perturbation solely based on observing the output label of the targeted model, are still relatively rare and mostly use gradient-estimation strategies. In this work, we propose a pixel-wise decision-based attack algorithm that finds a distribution of adversarial perturbation through a reinforcement learning algorithm. We call this method Decision-based Black-box Attack with Reinforcement learning (DBAR). Experiments show that the proposed approach outperforms state-of-the-art decision-based attacks with a higher attack success rate and greater transferability.
更多
查看译文
关键词
Adversarial attack, Decision attack, Reinforcement Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要