# The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents

arXiv: https://arxiv.org/abs/2609.22818 · HTML: https://mlsanity.com/paper/2609.22818/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 7 references that are in the map.
- First posted on arXiv 19 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 6 of 6)

- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Defeating Prompt Injections by Design](https://mlsanity.com/paper/2503.18813/) (2025)
- [PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models](https://mlsanity.com/paper/2402.07867/) (2024)
- [A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memory](https://mlsanity.com/paper/2510.02373/) (2025)
- [From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents](https://mlsanity.com/paper/2606.04329/) (2026)
- [A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework](https://mlsanity.com/paper/2604.23338/) (2026)

## Abstract (arXiv)

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 developed a measurement setup that keeps the memory backend, retrieval process, and judge consistent across different conditions, changing only the defense itself. We test each condition three times across five conversations to distinguish the defense's real effects from noise inherent in the pipeline's runs, which remains significant even at temperature zero. Across three write-time defenses (input sanitization, provenance checking, and LLM-based anomaly detection) and one read-time defense (reranking), tested on entirely benign traffic, the write-time defenses show no utility cost we can resolve, with 95% confidence intervals spanning roughly +/-4.5 points and including zero. The reranker is different: it lowers core accuracy by 4.4 points (95% CI [-9.0,-0.05], bootstrap; McNemar p=0.064), a result that survives replication but sits at the edge of our resolution. Its clearer cost is mechanical rather than statistical. On conversations containing no attack, the reranker quarantines legitimate memories on 33.6% of adjudicated items, reaching as many as 106 false quarantines in a single conversation, at 2.7% token overhead. Stacking all four defenses does not compound this cost: the combined condition's accuracy loss is smaller, and its confidence interval includes zero, suggesting the write-time defenses may partly offset what the reranker discards. Where a defense intercepts the pipeline, not whether it uses an LLM, appears to determine its benign-case price.