作者位次 #2/6ACL 2026Poster· Natural Language Processing
Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Wentao Zhang · Yan Zhuang · ZhuHang Zheng · Mingfei Zhang · Jiawen Deng · Fuji Ren
摘要
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 ind...