KV Cache Reuse in LLM Reasoning Traces Enables Stealthy Poisoning

Mon, 19 Oct 2026 18:41:36 +0000

Engineer — Learn: Novel black-box attack class against LLM inference systems using shared KV caches for reasoning trace reuse — engineers building or deploying such systems should audit whether their architecture exposes shared cache state across users or sessions, and treat this as a design constraint before enabling reasoning-cache reuse features.
SOC/IR — Skip
Leader — Skip

Cache-Poisoning on CuraSec