כתבה
arXiv cs.AI ·
AgentHijack: פצח ראייתי נגד CUAs
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents
המחברים הציגו תשתית לבדיקה של פצחי ראייה שמסוגלים להזיק ל-CUAs. הם ניסו את הפצחים ב-5 רכיבי GUI-agent ו-VLM.
תקציר מקורי באנגליתarXiv:2609.09212v1 Announce Type: cross Abstract: This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית