Chat-only attack poisons reused reasoning KV caches in LLMs
R2ECAP reached up to 79% success on three open-weight models and beat HijackKV in eight of nine constrained settings.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #llm-poisoning
Finding Nemo(Claw): Networking Issue Allows for LLM Poisoning in OpenClaw
A networking flaw in Nvidia tooling lets attackers reach OpenClaw's local model server unauthenticated via the Ollama API, enabling persistent LLM poisoning.