Another 232papers do not have category tags yet and are not included in filtered results.
重测并扩展对 AI Agent 的提示注入，并用 Agent Card 欺骗操纵 A2A 选择
作者在自建的 LangChain、AutoGen 和 A2A 系统上重测提示注入，并改 Agent Card 看选择是否偏移。摘要称试验主要凸显单智能体弱点，同时把攻击扩到多智能体。
提出 StegoMemory，评测智能体持久记忆作为跨会话隐写信道
Abstract研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。
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。
提出 CITA 三阶段框架，生成可绕过毒性检测器的中文隐式毒性文本
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.
Propose Blindfold, jailbreaking embodied LLMs with action-level manipulation
Blindfold is a no-box attack against embodied LLM planning modules, rewriting malicious intent into seemingly benign action sequences.
Propose Thought Virus, which propagates preferences along multi-agent messages via subliminal prompts.
Thought Virus puts subliminal prompting into multi-agent communication, to see whether a single-point deviation spreads across the network without naming the target concept.
用 OpenRAG-Soc 评测社交网页 RAG 的间接提示注入与检索投毒
提出双重隐写越狱 Odysseus，用图像隐写绕过多模态系统安全过滤器
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。