mlsanityData to 14 Oct 2026

RADAR: Defending RAG Dynamically against Retrieval Corruption

arXiv 2605.22041 ↗First posted 21 May 2026cs.CR cs.LGcited by 1

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing static-oriented defenses struggle to handle evolving threats and incur prohibitive storage costs in dynamic settings. We propose RADAR, a framework that models reliable context selection as a graph-based energy minimization problem, solved exactly via Max-Flow Min-Cut. By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts. Experiments on a novel dynamic dataset show that RADAR achieves superior robustness and response quality with minimal storage overhead compared to the baselines.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 26 of its 35 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

26 of 35 references.

Closest ancestors · 11

Same direction, newest first

  1. 2026Confundo: Learning to Generate Robust Poison for Practical RAG Systems6 Feb
  2. 2025ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search27 Sep
  3. 2025Your RAG is Unfair: Exposing Fairness Vulnerabilities in Retrieval-Augmented Generation via Backdoor Attacks26 Sep
  4. 2025AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt18 Sep
  5. 2025DeRAG: Black-box Adversarial Attacks on Multiple Retrieval-Augmented Generation Applications via Prompt Injection20 Jul
  6. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization10 Apr
  7. 2025Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models3 Feb
  8. 2025Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems20 Jan
  9. 2024Backdoored Retrievers for Prompt Injection Attacks on Retrieval Augmented Generation of Large Language Models18 Oct
  10. 2024Certifiably Robust RAG against Retrieval Corruption24 May
  11. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations22 Apr

Other references · 15

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,254
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  8. 2024Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inferencecited by 554
  9. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  10. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 101
  11. 2024Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Modelscited by 58
  12. 2024Retrieval-Augmented Generation with Estimation of Source Reliabilitycited by 19
3 more
  1. 2025Stream RAG: Instant and Accurate Spoken Dialogue Systems with Streaming Tool Usagecited by 15
  2. 2025WINELL: Wikipedia Never-Ending Updating with LLM Agentscited by 5
  3. 2025From Static to Dynamic: A Streaming RAG Approach to Real-time Knowledge Basecited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attacks
  2. 2026Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
  3. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
  4. 2026Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
  5. 2025RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation
  6. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
  7. 2024Towards More Robust Retrieval-Augmented Generation: Evaluating RAG Under Adversarial Poisoning Attacks
  8. 2026RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution