RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis

Xue Tan, Hao Luan, Mingyu Luo, Xiaoyan Sun 0003, Ping Chen 0003, Jun Dai. RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis. In Christos Christodoulopoulos 0001, Tanmoy Chakraborty 0002, Carolyn Rose, Violet Peng, editors, Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China, November 4-9, 2025. pages 12999-13011, Association for Computational Linguistics, 2025. [doi]

@inproceedings{TanLLSCD25,
  title = {RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis},
  author = {Xue Tan and Hao Luan and Mingyu Luo and Xiaoyan Sun 0003 and Ping Chen 0003 and Jun Dai},
  year = {2025},
  url = {https://aclanthology.org/2025.findings-emnlp.698/},
  researchr = {https://researchr.org/publication/TanLLSCD25},
  cites = {0},
  citedby = {0},
  pages = {12999-13011},
  booktitle = {Findings of the Association for Computational Linguistics: EMNLP 2025, Suzhou, China, November 4-9, 2025},
  editor = {Christos Christodoulopoulos 0001 and Tanmoy Chakraborty 0002 and Carolyn Rose and Violet Peng},
  publisher = {Association for Computational Linguistics},
  isbn = {979-8-89176-335-7},
}