Beyond Explicit Refusals: Soft-Failure Attacks on Retrieval-Augmented Generation
Wentao Zhang, Yan Zhuang, ZhuHang Zheng, Mingfei Zhang, Jiawen Deng, Fuji Ren
Recommendation Score
Research context
Topics
RAG
Paper type
Benchmark
Best for
Useful for both
arXiv categories
Why It Matters
DEJA exposes stealthy RAG failures that mimic valid responses, forcing a paradigm shift in security evaluation—essential for deploying reliable RAG systems that must detect subtle, non-obvious degradation.
Abstract
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. We propose Deceptive Evolutionary Jamming Attack (DEJA), an automated black-box attack framework that generates adversarial documents to trigger such soft failures by exploiting safety-aligned behaviors of large language models. DEJA employs an evolutionary optimization process guided by a fine-grained Answer Utility Score (AUS), computed via an LLM-based evaluator, to systematically degrade the certainty of answers while maintaining high retrieval success. Extensive experiments across multiple RAG configurations and benchmark datasets show that DEJA consistently drives responses toward low-utility soft failures, achieving SASR above 79\% while keeping hard-failure rates below 15\%, significantly outperforming prior attacks. The resulting adversarial documents exhibit high stealth, evading perplexity-based detection and resisting query paraphrasing, and transfer across model families to proprietary systems without retargeting.