SOURCE-LINKED INTELLIGENCE

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

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 ins

Read original source ↗ Open in workspace

recordType

paper

region

Global