RADAR: Defending RAG Dynamically against Retrieval Corruption
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910245059559424 |
|---|---|
| author | Chen, Ziyuan Lyu, Yueming Liu, Yi Han, Weixiang Dong, Jing Shan, Caifeng Tan, Tieniu |
| author_facet | Chen, Ziyuan Lyu, Yueming Liu, Yi Han, Weixiang Dong, Jing Shan, Caifeng Tan, Tieniu |
| contents | 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 By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts.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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_22041 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RADAR: Defending RAG Dynamically against Retrieval Corruption Chen, Ziyuan Lyu, Yueming Liu, Yi Han, Weixiang Dong, Jing Shan, Caifeng Tan, Tieniu Cryptography and Security Machine Learning 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 By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts.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. |
| title | RADAR: Defending RAG Dynamically against Retrieval Corruption |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2605.22041 |