Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG

ArXi:2506.04390v2 Announce Type: replace-cross Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable detection and mitigation. We formalize a distinguishability-based security game to quantify stealth for such attacks. If a few poisoned passages control the response, they must bias the inference process than the benign ones, inherently compromising stealth.