Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping

Zhenbo Shi, Wei Yang, Zhenbo Xu, Zhidong Yu, Liusheng Huang

Abstract: In the field of object detector attacks, previous methods primarily rely on fixed gradient optimization or patch-based cover techniques, often leading to suboptimal attack performance and excessive distortions. To address these limitations, we propose a novel attack method, Interactive Reinforcement-based Sparse Attack (IRSA), which employs Reinforcement Learning (RL) to discover the vulnerabilities of object detectors and systematically generate erroneous results. Specifically, we formulate the process of seeking optimal margins for adversarial examples as a Markov Decision Process (MDP). We tackle the RL convergence difficulty through innovative reward functions and a composite optimization method for effective and efficient policy training. Moreover, the perturbations generated by IRSA are more subtle and difficult to detect while requiring less computational effort. Our method also demonstrates strong generalization capabilities against various object detectors. In summary, IRSA is a refined, efficient, and scalable interactive, iterative, end-to-end algorithm.