# memory
標記為「memory」的 8 篇文章
Vector-based 記憶體投毒
對代理系統中之 vector-based 記憶體儲存投毒，於檢索時注入偽造脈絡。
跨代理記憶體攻擊
在多代理系統中跨代理傳播對抗性記憶、共享記憶體投毒與記憶體信任邊界違反的攻擊。
實驗室: 代理 記憶 操控
動手實驗室,主題為injecting persistent instructions into an agent's memory與context that affect future interactions與conversations.
代理 記憶 操控
利用 persistent memory in LLM agents to plant false context that persists across sessions.
實驗室: 代理 記憶 投毒
動手lab exploring how conversational memory in AI agents can be poisoned to alter future behavior,inject persistent instructions,exfiltrate data across sessions.
Memory Persistence 攻擊 詳解
Walkthrough of achieving persistent memory manipulation in agent systems for cross-session influence.
LangChain Application 安全 Testing
End-to-end walkthrough for security testing LangChain applications: chain enumeration, prompt injection through chains, tool and agent exploitation, retrieval augmented generation attacks, and memory manipulation.
Microsoft Semantic Kernel 安全 Testing
End-to-end walkthrough for security testing Semantic Kernel applications: kernel enumeration, plugin exploitation, planner manipulation, memory and RAG assessment, and Azure integration security review.