STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks

Paper recorded by Signals 4 on 2026-10-23 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-23 on arXiv · recorded by Signals 4 on 2026-10-26

Category: cs.CV · 计算机视觉 · first seen 2026-10-26

Abstract

We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these perturbations through a lightweight greedy add-and-refine procedure. Across diverse image classifiers, STROKE achieves high attack success with low query counts at nominal 1--2\% area settings, showing favorable performanc

Read on arXiv →