MRMMIA is a multi-recall-probe membership inference attack that extracts signals from chat agent memory and outperforms baselines in black-, gray-, and white-box settings.
The good and the bad: Exploring privacy issues in retrieval-augmented generation (RAG)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.
PRAG delivers end-to-end private RAG with 72-74% recall via non-interactive homomorphic approximations, interactive client assistance, and operation-error estimation to preserve ranking quality.
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
GuarantRAG improves RAG accuracy up to 12.1% and cuts hallucinations 16.3% by decoupling parametric reasoning from evidence integration via contrastive DPO and joint decoding.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
citing papers explorer
-
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.