Stealthy Poisoning Attacks via Reused KV Cache of Reasoning
Reusing KV caches from reasoning traces — a common LLM inference optimisation — opens a stealthy poisoning vector that evades standard output monitoring, complicating RAG-style deployments.
Summary written by editorial AI · Source link below
arXiv:2610.22873v1 Announce Type: new Abstract: Modern large language model (LLM) systems reuse key-value (KV) caches to accelerate inference. Recent work has shown that reusing KV caches from reasoning traces can also improve task performance, similar to retrieval-augmented generation (RAG). We demonstrate that this form of KV cache reuse introduces new poisoning vulnerabilities. We propose R$^2$ECAP (Reused Reasoning-Cache Poisoning), a black-box attack that plants poisoned reasoning traces s
Editorial Analysis
Enterprises optimising LLM inference with cached reasoning traces may unknowingly introduce a poisoning surface that standard safety checks do not cover.
Audit KV-cache reuse policies in production LLM systems and implement integrity checks on cached reasoning artifacts.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d