SentinelRAG: Synthetic Sentinel Knowledge for RAG Database Copyright Protection
For developers of proprietary RAG databases, SentinelRAG provides a robust watermarking method that avoids polluting knowledge with misinformation or fragile patterns, unlike prior approaches.
SentinelRAG embeds style-consistent fictitious knowledge into RAG databases to enable copyright protection, achieving statistically significant detection (p < 10^{-5}) at a 0.1% injection rate across datasets up to 8.8M documents, with negligible interference on legitimate queries.
Protecting proprietary RAG databases from unauthorized redistribution is challenging: existing watermarking methods either inject fabricated relations between real entities, polluting the knowledge base with misinformation, or embed fragile lexical patterns that adversarial paraphrasing easily removes. We propose SentinelRAG, a watermarking framework that embeds style-consistent but fictitious knowledge entries into the RAG database. Our key insight is that synthetic knowledge describing fictitious entities is unlikely to be retrieved by legitimate queries, yet can be reliably triggered through targeted probes known only to the data owner. Experiments on four datasets ranging from 2.9k to 8.8M documents demonstrate that SentinelRAG achieves statistically significant detection $p < 10^{-5}$ across all tested configurations at only a 0.1% injection rate. Compared to the state-of-the-art, our method significantly reduces the false detection rate while maintaining negligible interference with legitimate user queries.