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

arXiv:2609.22818 · cs.CR, cs.AI · Submitted 2026-09-19 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-09-19

Updated: 2026-09-19

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 2× in this paper · explained in 1 episode
• Core — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs