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

researchr

You are not signed in
Sign in
Sign up

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]

This author has not been identified. Look up 'Xue Tan' in GoogleThis author has not been identified. Look up 'Hao Luan' in GoogleThis author has not been identified. Look up 'Mingyu Luo' in GoogleThis author has not been identified. Look up 'Xiaoyan Sun 0003' in GoogleThis author has not been identified. Look up 'Ping Chen 0003' in GoogleThis author has not been identified. Look up 'Jun Dai' in Google

runs on WebDSL