arXiv (All)
open access
Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents
In LLM agents with persistent memory, whether a model stores an injected instruction and whether it later acts on it are separable safety properties. We call this the injection-execution dissociation. We evaluate 29 frontier endpoints with the malicious document in the retrieval corpus (N=10 each, f
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- MIND: Lightweight and Effective Memory Injection Defense for LLM Agents via Intent-Aware Information Bottleneck#1341488
- After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents#1412391
- After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents#1394140
- Transferable End-to-End Optimization for Indirect Long-Term Memory Poisoning in LLM Agents#819965
- From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents#1119205
Record · ID 1447150
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive