CleanBase identifies malicious documents in RAG databases by detecting cliques in a semantic similarity graph constructed using embedding models and a statistical threshold.
CPA-RAG: Covert poisoning attacks on retrieval- augmented generation in large language models
3 Pith papers cite this work. Polarity classification is still indexing.
fields
cs.CR 3years
2026 3representative citing papers
RAGShield detects all numerical manipulations in government RAG systems via pattern-based value extraction and cross-source verification, achieving 0% attack success rate on 430 real IRS-derived attacks where embedding defenses miss 79-90%.
RefineRAG achieves 90% attack success on NQ by generating toxic seeds then optimizing them via retriever-in-the-loop word refinement, outperforming prior methods on effectiveness and naturalness.
citing papers explorer
-
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
CleanBase identifies malicious documents in RAG databases by detecting cliques in a semantic similarity graph constructed using embedding models and a statistical threshold.
-
RAGShield: Detecting Numerical Claim Manipulation in Government RAG Systems
RAGShield detects all numerical manipulations in government RAG systems via pattern-based value extraction and cross-source verification, achieving 0% attack success rate on 430 real IRS-derived attacks where embedding defenses miss 79-90%.
-
RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement
RefineRAG achieves 90% attack success on NQ by generating toxic seeds then optimizing them via retriever-in-the-loop word refinement, outperforming prior methods on effectiveness and naturalness.