# memory
9 artikelengetagd met “memory”
Vector-gebaseerde geheugenvergiftiging
Het vergiftigen van vector-gebaseerde geheugenopslagplaatsen in agent-systemen om valse context in het ophalen te injecteren.
Cross-Agent Memory-aanvallen
Het exploiteren van gedeeld geheugen en gedeelde context tussen agents in multi-agentarchitecturen.
Lab: manipulatie van agentgeheugen
Hands-on lab for injecting persistent instructions into an agent's memory and context that affect future interactions and conversations.
Manipulatie van agentgeheugen
Exploit persistent memory in LLM agents to plant false context that persists across sessions.
Lab: poisoning van agentgeheugen
Hands-on lab exploring how conversational memory in AI agents can be poisoned to alter future behavior, inject persistent instructions, and exfiltrate data across sessions.
Cross-context injection (prompt injection)
Prompt injection-technieken die over contextgrenzen heen blijven bestaan: ze overleven conversatie-resets, sessiewisselingen, geheugengrenzen en handoffs tussen meerdere agents.
Walkthrough: aanval op geheugenpersistentie
Walkthrough of achieving persistent memory manipulation in agent systems for cross-session influence.
Beveiligingstesten van LangChain-applicaties
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.
Beveiligingstesten van Microsoft Semantic Kernel
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.