Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Detecting and Localizing Segment-Level Poisoning in Multi-Source LLM-Agent Inputs
Xue Tan, Changhui Wang, Sanrui Yang +6
Modern large language model (LLM) agents often construct prompts by aggregating retrieved passages, user reviews, and documents from multiple external sources. This paradigm expose…
cs.CR2024
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
Xue Tan, Hao Luan, Mingyu Luo +3
Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database, enabling them to produce responses that are more acc…