SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Aug 25, 2026 · UTC

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 ro

Read original source ↗ Open in workspace

recordType

paper

region

Global