DP 2 -RAG: An Efficient Full-Process Differential Privacy Implementation in Retrieval-Augmented Generation
- 1 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21, 8182-8197
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62532016)
- National Key Research and Development Program of China (2024YFF0908104)
- Collaborative Tackling Project of the Yangtze River Delta Sci-Tech Innovation Community (2024CSJGG01500)
- Natural Science Foundation of Shanghai (25ZR1402211)
- Ant Group (2024CSJGG01500)
- Ant Group
This publication has 12 references indexed in Scilit:
- RAG with Differential Privacy2025
- Mitigating privacy risks in Retrieval-Augmented Generation via locally private entity perturbationInformation Processing & Management, 2025
- A survey on large language model (LLM) security and privacy: The Good, The Bad, and The UglyHigh-Confidence Computing, 2024
- Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A SurveyACM Computing Surveys, 2023
- BioASQ-QA: A manually curated corpus for Biomedical Question AnsweringScientific Data, 2023
- Information Leakage in Embedding Models2020
- Trusted Execution Environments: Properties, Applications, and ChallengesIEEE Security & Privacy, 2020
- Enhancing Graph Kernels via Successive Embeddings2018
- Machine Learning Models that Remember Too Much2017
- Mechanism Design via Differential Privacy2007