Practical Region-level Attack against Segment Anything Models

arXiv:2404.08255v1 Announce Type: cross
Abstract: Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM against adversarial attacks is a critical concern. While recent works have explored adversarial attacks against a pre-defined prompt/click, their threat model is not yet realistic: (1) they often assume the user-click position is known to the attacker (point-based attack), and …

adversarial adversarial attacks applications arxiv attack attacks click critical cs.cr cs.cv image prompt robustness sam segment segmentation single target