AI RESEARCH

Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation

arXiv CS.AI

ArXi:2604.18663v1 Announce Type: cross Existing jamming attacks on Retrieval-Augmented Generation (RAG) systems typically induce explicit refusals or denial-of-service behaviors, which are conspicuous and easy to detect. In this work, we formalize a subtler availability threat, termed soft failure, which degrades system utility by inducing fluent and coherent yet non-informative responses rather than overt failures.