RADAR: Defending RAG Dynamically against Retrieval Corruption
Ziyuan Chen, Yueming Lyu, Yi Liu, Weixiang Han, JING DONG, Caifeng Shan, Tieniu Tan
Abstract
While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks. Existing static-oriented defenses struggle to handle evolving threats and incur prohibitive storage costs in dynamic settings. We propose RADAR, a framework that models reliable context selection as a graph-based energy minimization problem, solved exactly via Max-Flow Min-Cut. By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts. Experiments on a novel dynamic dataset show that RADAR achieves superior robustness and response quality with minimal storage overhead compared to the baselines.
BibTeX
@inproceedings{
chen2026radar,
title={{RADAR}: Defending {RAG} Dynamically against Retrieval Corruption},
author={Ziyuan Chen and Yueming Lyu and Yi Liu and Weixiang Han and Jing Dong and Caifeng Shan and Tieniu Tan},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=fT3laNA1AO}
}