Survey maps safety and security threats of autonomous computer-using agents

A new survey paper categorizes the safety and security threats posed by Computer-Using Agents (CUAs). These agents, powered by LLMs, can autonomously interact with software and interfaces, presenting novel risks. The paper outlines a taxonomy of these threats and proposes defensive strategies, aiming to guide future research and practical deployment of secure CUAs. AI

影响 Provides a structured foundation for understanding and mitigating novel safety and security risks in autonomous AI agents.

排序理由 This is a survey paper on safety and security threats of AI agents.

在 arXiv cs.CL 阅读 →

• arXiv
• Computer-Using Agents
• JARVIS
• LLM
• Ultron

• 论文
• 安全

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →