User-Entity Differential Privacy in Learning Natural Language Models
Not on the map. Why?
Abstract (arXiv)
In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models (NLMs). To preserve UeDP, we developed a novel algorithm, called UeDP-Alg, optimizing the trade-off between privacy loss and model utility with a tight sensitivity bound derived from seamlessly combining user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 48 references that are in the map. First posted on arXiv 1 Nov 2022.
Builds on
22 of 48 references.
References · 22
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Advances and Open Problems in Federated Learningcited by 3,021
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
- 2020Extracting Training Data from Large Language Modelscited by 2,144
- 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
- 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 719
- 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
- 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
- 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
- 2017Regularizing and Optimizing LSTM Language Modelscited by 205
10 more
- 2014Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Boundscited by 104
- 2016Minimax Optimal Procedures for Locally Private Estimationcited by 103
- 2020Training Production Language Models without Memorizing User Datacited by 68
- 2020Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairnesscited by 66
- 2019Local Differential Privacy for Deep Learningcited by 46
- 2020Towards Differentially Private Text Representationscited by 28
- 2019The Value of Collaboration in Convex Machine Learning with Differential Privacycited by 24
- 2019PrivFT: Private and Fast Text Classification with Homomorphic Encryptioncited by 12
- 2019Element Level Differential Privacy: The Right Granularity of Privacycited by 6
- 2020DP-Cryptography: Marrying Differential Privacy and Cryptography in Emerging Applicationscited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.