EPS
← All batches·2605.22041

RADAR: Defending RAG Dynamically against Retrieval Corruption

topic: current_projecttop score: 100released: 2026-05-22first surfaced: 2026-05-22arXivPDFthreats2026-05-22

Authors: Ziyuan Chen, Yueming Lyu, Yi Liu et al.

arXiv · PDF

Summary

arXiv:2605. 22041v1 Announce Type: new Abstract: While RAG systems are increasingly deployed in dynamic web search, temporal volatility amplifies their vulnerability to adversarial attacks.

Relevance

Read next because RADAR: Defending RAG Dynamically against Retrieval Corruption overlaps with clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, eval, line, compare, model. Source: arxiv cs.CR (Cryptography and Security).

Threat model

Potential threat/caveat for clean result "LoRA persona trained on alone emits at 23.5% when a co-trained partner learns ..., vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)": this item discusses robustness, adversarial.

Abstract

arXiv:2605.22041v1 Announce Type: new 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 By incorporating a Bayesian memory node, RADAR recursively updates a belief state instead of archiving raw historical documents, effectively balancing stability against attacks with adaptability to genuine knowledge shifts.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.