arXiv (All)
open access
The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
Memory-poisoning defenses for LLM agents are typically evaluated by their ability to prevent attacks. However, the traffic they process is rarely adversarial. The cost of implementing a defense is paid with each interaction, while its benefits are only seen in a small percentage of cases. We develop
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
- MemPoison: Bypassing Selective Memory Mechanisms to Plant Backdoors in LLM Agents#1118580
- Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows#1049525
- When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-offs#405541
- EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium#1131525
- Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents#985213
Record · ID 1037501
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