arXiv Artificial Intelligence

AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

1 hour ago 11.09.2026 07:00 👁 2 views
AgentHijack: Visual Patch Attacks on Multimodal Computer-Use Agents

Quick summary

arXiv: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

Key takeaways

  • arXiv: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

Why it matters

This model development creates a new option for users and a new testing obligation for developers. A fixed evaluation set comparing quality, cost and failure behavior is more useful than launch claims.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗