AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems by Exploiting Knowledge Asymmetry

Yufei Chen, Yao Wang, Haibin Zhang, Tao Gu

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

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 q2 (explicit retrieved-content prompt) to q1 (ablation)adversarial query · HCMESR: 55.56% -> 93.55%Improved
add q2 to q1 (ablation)adversarial query · EEESR: 81.30% -> 95.65%Improved
add q2 to q1 (ablation)adversarial query · NQESR: 52.94% -> 80.00%Improved
use knowledge-asymmetry similarity features plus DNN instead of the best baseline (LLM-based judgment)privacy sentence identification · HCMESR: 65.22% -> 93.55%Improved
use knowledge-asymmetry features plus DNN instead of the best baseline (LLM-based judgment)privacy sentence identification · NQ (multi-domain)F1-score: 43.90% -> 84.21%Improved
swap standard LLM used for comparison from LLaMA3.1-8B to Qwen3-8B or GPT-4o (ablation)attack framework · HCMESR: 93.55% -> 85.71% (Qwen3-8B), 88.89% (GPT-4o)Hurt
swap standard LLM used for comparison from LLaMA3.1-8B to GPT-4o (ablation)attack framework · NQESR: 80.00% -> 85.71%Improved
swap retriever bge-large-en for e5-large-v2 or gte-large (ablation)attack framework · HCMESR: 93.55% -> 94.12% / 94.44%No clear effect
swap retriever bge-large-en for e5-large-v2 (ablation)attack framework · EEESR: 95.65% -> 82.14%Hurt
swap retriever bge-large-en for e5-large-v2 (ablation)attack framework · NQESR: 80.00% -> 84.62%Improved
use a different RAG LLM (Qwen3-8B or GPT-4o) instead of LLaMA3.1-8B (ablation)attack framework · NQESR: 80.00% -> 87.50% (Qwen3-8B), 76.73% (GPT-4o)Mixed
vary RAG model size (8B, 70B, 405B) and temperature (0.3, 0.6, 0.9) (ablation)attack framework · HCM/EE/NQESRNo 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