BeClaude
Research2026-04-30

A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

Source: Arxiv CS.AI

arXiv:2505.10924v4 Announce Type: replace-cross Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of...

arxivpapersagentssafety