Jul 31, 2024 · We propose a local black-box attack algorithm based on salient region localization called Local Imperceptible Random Search (LIRS).

Nov 29, 2019 · We propose the Square Attack, a score-based black-box l_2- and l_\infty-adversarial attack that does not rely on local gradient information.

Search- ing over the corners allows to apply discrete optimization techniques to generate adversarial attacks, significantly improving the query efficiency.

We aim at building a comprehensive benchmark of black-box adversarial attacks, called BlackboxBench. It mainly provides: 1) a unified, extensible and modular- ...

Oct 22, 2024 · To address these problems and improve black-box attacks, we propose two prior-guided random gradient-free (PRGF) algorithms based on biased ...

Deep neural networks are vulnerable to adversarial examples, even in the black- box setting where the attacker only has query access to the model output.

Jan 4, 2021 · A novel framework to perturb the discriminative areas of clean examples only within limited queries in black-box attacks with a high attack success rate.

This paper introduces a novel black-box ensemble attack algorithm (DSWEA) that combines the Ranking Variance Reduced (RVR) ensemble strategy with the Dynamic ...

To improve the efficiency of previous methods, we propose an evolutionary attack algorithm, which can model the local geometry of the search directions and ...

This paper proposes several modifications to the black-box adversarial attack SimBA to improve its query efficiency.