Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation

A new survey from arXiv (2608.24977v1) systematically maps attacks and defenses across the full Retrieval-Augmented Generation (RAG) pipeline, formalizing threat models over the corpus, retriever, and generator, and organizing attacks into accuracy, privacy, and fairness objectives. The survey reviews pipeline-aware defenses spanning retrieval, rerank, generation, and traceback stages, and summarizes robustness benchmarks and explainability methods for evaluating RAG robustness.

arXiv:2608.24977v1 Announce Type: cross Abstract: Retrieval-Augmented Generation RAG enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introduces new robustness and security risks, including corpus poisoning, backdoor attacks, privacy leakage, and fairness violations. Despite rapid progress in this area, existing surveys remain limited in their treatment of attacker objectives, threat models, and stage-specific defenses across the full RAG pipeline. This survey presents a unified and pipeline-aware overview of RAG robustness. We formalize threat models over the corpus, retriever, and generator, and organize attacks into three main objectives: accuracy, privacy, and fairness. We further review defenses from a pipeline-aware perspective, covering the retrieval, rerank, generation, and traceback stages. In addition, we summarize robustness benchmarks and explainability methods for more deeply evaluating and explaining RAG robustness.