Vincent Siu

1. AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents
   2025/05/09 by Vincent Siu, Wang, Zhun, Zhe Ye +14 · 11 citations
   Computer Science · Social Sciences · #Access Control and Trust #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Security and Verification in Computing
2. Agents' Last Exam
   2026/06/03 by Yiyou Sun, Xinyang Han, Weichen Zhang +306 · 4 voices
   #cs.AI #cs.CL #cs.LG
3. Agent Security Needs Redefinition through a Holistic Framework
   2026/07/24 by Vincent Siu, Jingxuan He, Kyle Montgomery +3
   #cs.CR #cs.AI