Proceedings of the AAAI Conference on Artificial Intelligence
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
Haowei Wang*, Rupeng Zhang*, Junjie Wang, Mingyang Li, Yuekai Huang, Dandan Wang, Qing Wang
Co-first author · November 2025
Summary
A framework that unifies gradient-based poisoning against RAG systems by jointly optimizing the attack for the retriever and the generator, rather than treating them as two separate targets.
Built with:LLM SecurityNLPAdversarial Attack