Another 227papers do not have category tags yet and are not included in filtered results.
用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行
作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。
提出类型化溯源与断言护栏，约束持久 Agent 释放自传断言
提出针对 Agent Harness 的上下文特权提升攻击
评测编码 Agent 记忆文件中提示注入的跨会话影响
Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。
提出潜伏记忆投毒，诱导 Agent 把外部文档写成持久伪造记忆
sleeper memory poisoning 研究带持久记忆的 LLM 助手：外部文档能否让助手存下一则伪造的用户记忆，并在原文档消失后的新会话里被取回、用来改变回复或动作。
Proposes LAAF, which automatically attacks LPCI vulnerabilities in agent systems in stages
The authors state that LAAF is an automated red-teaming framework built specifically for LPCI in agentic LLMs. The issue to address is that encoded, delayed, and conditionally triggered payloads can persist in memory or RAG and re-enter across sessions, whereas Garak and PyRIT do not use the previous round's breakthrough results to seed the next stage across the six stages.
提出 LPCI，把延迟条件载荷写入记忆与检索库以跨会话触发
作者把LPCI定义为针对智能体逻辑执行、记忆留存和工具集成的跨阶段漏洞类，而不是单次输入上的提示改写。