A large body of research has focused on adversarial attacks which require to modify all input features with small $l_2$- or $l_\infty$-norms. In this paper we instead focus on query-efficient sparse attacks in the black-box setting. Our versatile framework, Sparse-RS, based on random search achieves state-of-the-art success rate and query efficiency for different sparse attack models such as $l_0$-bounded perturbations (outperforming established white-box methods), adversarial patches, and adversarial framing. We show the effectiveness of Sparse-RS on different datasets considering problems from image recognition and malware detection and multiple variations of sparse threat models, including targeted and universal perturbations. In particular Sparse-RS can be used for realistic attacks such as universal adversarial patch attacks without requiring a substitute model. The code of our framework is available at https://github.com/fra31/sparse-rs.

提出了一种基于随机搜索的多用途框架 Sparse-RS，可用于黑盒设置下的基于得分的稀疏目标攻击和非目标攻击，并达到了多个稀疏攻击模型的最先进的成功率和查询效率。

Sparse-RS: 一种用于高效查询稀疏黑盒对抗攻击的通用框架