@inproceedings{yao-etal-2025-ecosaferag,
    title = "{E}co{S}afe{RAG}: Efficient Security through Context Analysis in Retrieval-Augmented Generation",
    author = "Yao, Ruobing  and
      Zhang, Yifei  and
      Song, Shuang  and
      Gao, Neng  and
      Tu, Chenyang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.215/",
    doi = "10.18653/v1/2025.findings-emnlp.215",
    pages = "4034--4050",
    ISBN = "979-8-89176-335-7",
    abstract = "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 $\times$ latency, 48{\%}-80{\%} token reduction versus Vanilla RAG)."
}