AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation

Qinfeng Li, Miao Pan, Ke Xiong, Ge Su, Zhiqiang Shen, Yan Liu, Sun Bing, Hao Peng, Xuhong Zhang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add RAGFort dual-path defenseRAG system, Qwen-14B · HealthCareMagic RAG-ThiefCRR (%): 57.16 -> 27.96Improved
add RAGFort dual-path defenseRAG system · All datasets and modelsrelative mean CRR: 1x -> 0.51xImproved
add re-ranking protection (inter-class)RAG system · All datasets and modelsrelative mean CRR: 1x -> 0.91xNo clear effect
add summarization protection (intra-class)RAG system · All datasets and modelsrelative mean CRR: 1x -> 0.87xNo clear effect
add contrastive reindexing to cascade-only defense (ablation)RAGFort · All datasets and modelsrelative mean CRR: 0.83x -> 0.51xImproved
add cascade generation to reindexing-only defense (ablation)RAGFort · All datasets and modelsrelative mean CRR: 0.75x -> 0.51xImproved
add contrastive reindexing only (ablation)RAG system, Qwen-14B · Math QA RAG-ThiefCRR (%): 70.31 -> 54.61Improved
add cascade generation only (ablation)RAG system, Qwen-14B · Math QA RAG-ThiefCRR (%): 70.31 -> 65.63No clear effect
add RAGFort (ablation)RAG system, Qwen-14B · HealthCareMagicanswer accuracy (%): 68.16 -> 66.57Hurt
add RAGFortRAG system, Qwen-14B · Math QAanswer accuracy (%): 85.31 -> 82.81Hurt
add RAGFort cascade with smaller draft modelRAG system, Qwen-14B · HealthCareMagicFLOPs (T): 38.03 -> 19.40Improved
add RAGFort with same draft and reference modelRAG system, DeepSeek-R1-8B · HealthCareMagicFLOPs (T): 20.37 -> 20.83No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy