Work

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

Year: 2026

Type: conference-paper

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.Finally, we highlight open challenges and future directions for building trustworthy RAG systems.To continuously track developments in this rapidly evolving field, we will also actively update a public repository at https://github.com/ coutMinh/A-Survey-on-RAG-Robustness.

Source: Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)

DOI: 10.18653/2026.findings-emnlp.1269