{"slug": "mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact", "title": "Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution", "summary": "Researchers propose KFS-RAG, a defense that mitigates database leakage in Retrieval-Augmented Generation (RAG) systems by reformulating retrieved context using keyword-grounded fact substitution. The method identifies influential keywords via attention rollout and causal perturbation, then uses an auxiliary LLM to generate sanitized facts, reducing leakage risk under prompt injection attacks while maintaining accuracy. The work is published on arXiv (2608.21656v1).", "body_md": "arXiv:2608.21656v1 Announce Type: new\nAbstract: Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, which may mislead the retriever or generator to expose sensitive database contents. To address this issue, we propose KFS-RAG, a defense that mitigates information leakage by reformulating the retrieved context. Specifically, our method first identifies a small set of influential keywords from the retrieved context via an attention rollout plus a causal perturbation mechanism. These keywords are then used to guide an auxiliary LLM to generate a compact set of keyword-grounded facts from the retrieved passages. Finally, the original context is substituted with these curated facts, ensuring that the generator operates on sanitized evidence rather than the raw retrieved text. Experimental evaluations demonstrate that KFS-RAG significantly reduces the risk of database leakage under injection attacks while maintaining response accuracy and relevance. This work highlights a practical pathway toward building secure and trustworthy RAG systems.", "url": "https://wpnews.pro/news/mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact", "canonical_source": "https://arxiv.org/abs/2608.21656", "published_at": "2026-08-25 04:00:00+00:00", "updated_at": "2026-08-25 04:15:23.055695+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-research"], "entities": ["arXiv", "KFS-RAG"], "alternates": {"html": "https://wpnews.pro/news/mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact", "markdown": "https://wpnews.pro/news/mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact.md", "text": "https://wpnews.pro/news/mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact.txt", "jsonld": "https://wpnews.pro/news/mitigating-database-leakage-in-rag-systems-with-keyword-grounded-fact.jsonld"}}