all AI news
Practical Region-level Attack against Segment Anything Models
April 15, 2024, 4:44 a.m. | Yifan Shen, Zhengyuan Li, Gang Wang
cs.CV updates on arXiv.org arxiv.org
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 …
abstract adversarial adversarial attacks applications arxiv attacks click cs.cr cs.cv image practical prompt robustness sam segment segment anything segmentation type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US
Research Engineer
@ Allora Labs | Remote
Ecosystem Manager
@ Allora Labs | Remote
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US