作者位次 #2/9ACL 2026Poster· Natural Language Processing
JARVIS or Ultron? A Survey on the Safety and Security Threats of Computer-Using Agents
Ada Chen · Yongjiang Wu · Junyuan Zhang · Jingyu Xiao · Shu Yang · Jen-Tse Huang · Kun Wang · Wenxuan Wang · Shuai Wang
摘要
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 Computer-Using Agents (CUAs), capable of autonomously perfor...