Another 240papers do not have category tags yet and are not included in filtered results.
提出 LogInject 框架，评测日志分析中的被动提示注入及缓解
Abstract论文评估了 LLM 日志分析中的上下文污染风险，提出分片拼接等攻击与三层防御，指出必须结合架构隔离与人工介入。
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 Thought Virus，经潜意识提示使偏好沿多 Agent 消息传播
Thought Virus 把 subliminal prompting 放进多智能体通信，看单点偏差会不会在不点名目标概念时传到全网。
用简历中的不可见指令做间接提示注入，操纵招聘推荐
Abstract作者称推理在简单注入下会帮攻击圆谎，在不合逻辑的复杂注入下又会把欺骗漏出来。
提出 AST-ASIP ，把对抗指令植入编译器忽略区域以劫持代码评分
这篇工作把自动代码评分中的失败称为 Compliance Paradox：评分模型可以离开提交逻辑，转而执行嵌在可编译代码里的隐藏指令。
用 OpenRAG-Soc 评测社交网页 RAG 的间接提示注入与检索投毒
提出 DSAAP，以不可见文本对科学审稿 PDF 做间接提示注入