
























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 By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts.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.
| Subjects: | Cryptography and Security (cs.CR); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.22041 [cs.CR] |
| (or arXiv:2605.22041v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22041 arXiv-issued DOI via DataCite (pending registration) |
From: Ziyuan Chen [view email]
[v1]
Thu, 21 May 2026 06:25:46 UTC (512 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。