AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
AgentSentry: 通过时间因果诊断和上下文净化缓解LLM代理中的间接提示注入
机构 * Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University(航空信息安全与可信计算重点实验室、教育部、网络安全科学与工程学院、武汉大学) ; Department of Computer Science and Engineering, University at Buffalo, SUNY(计算机科学与工程系、布法罗大学、纽约州立大学) ; Department of Computer Science, College of Information Science and Technology, Jinan University(计算机科学系、信息科学与技术学院、济南大学) ; College of Cyber Security, Jinan University(网络安全学院、济南大学)
专题命中 评测与基准 :LLM(title,abstract);large language model(abstract);language model(abstract);分类 cs.AI
AI总结 AgentSentry通过时间因果诊断和上下文净化缓解LLM代理中的间接提示注入,有效消除攻击并保持实用性。
Comments 23 pages, 8 figures. Under review