Return
Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
DOI:10.1016/j.inffus.2025.103900.png)
Abstract
En 中文
• The first systematic study of data poisoning attacks on KG-RAG. • Developing a targeted attack strategy to complete adversarial inference chains. • Our attacks substantially degrade the performance of existing KG-RAG systems.
Journal
IF:
15.5
Papers:
4.1K
Citations:
2.7W

