mlsanityData to 14 Oct 2026

EcoSafeRAG: Efficient Security through Context Analysis in Retrieval-Augmented Generation

arXiv 2505.13506 ↗First posted 16 May 2025cs.CL cs.AIcited by 4

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) compensates for the static knowledge limitations of Large Language Models (LLMs) by integrating external knowledge, producing responses with enhanced factual correctness and query-specific contextualization. However, it also introduces new attack surfaces such as corpus poisoning at the same time. Most of the existing defense methods rely on the internal knowledge of the model, which conflicts with the design concept of RAG. To bridge the gap, EcoSafeRAG uses sentence-level processing and bait-guided context diversity detection to identify malicious content by analyzing the context diversity of candidate documents without relying on LLM internal knowledge. Experiments show EcoSafeRAG delivers state-of-the-art security with plug-and-play deployment, simultaneously improving clean-scenario RAG performance while maintaining practical operational costs (relatively 1.2× latency, 48%-80% token reduction versus Vanilla RAG).

Key facts. Cited by 4 papers 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 25 of its 46 references that are in the map. First posted on arXiv 16 May 2025.

Builds on

25 of 46 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024"Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models26 Jun
  2. 2024Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents9 Jun
  3. 2024Certifiably Robust RAG against Retrieval Corruption24 May

Other references · 22

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  6. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  7. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  8. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,216
  10. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  11. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  12. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
10 more
  1. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  2. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 318
  3. 2023RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Modelscited by 283
  4. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  5. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  6. 2024InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationalescited by 101
  7. 2024A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Modelscited by 100
  8. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 89
  9. 2023Information Retrieval: Recent Advances and Beyondcited by 49
  10. 2024Does RAG Introduce Unfairness in LLMs? Evaluating Fairness in Retrieval-Augmented Generation Systemscited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Benchmarking Poisoning Attacks against Retrieval-Augmented Generationcited by 18
  2. 2026Overcoming the Retrieval Barrier: Indirect Prompt Injection in the Wild for LLM Systemscited by 16
  3. 2026ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoningcited by 2
  4. 2026RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
  2. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
  3. 2025Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation
  4. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
  5. 2025SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
  6. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  7. 2026Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
  8. 2025Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems