# Learning Differentially Private Recurrent Language Models

arXiv: https://arxiv.org/abs/1710.06963 · HTML: https://mlsanity.com/paper/1710.06963/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Oct 2017.

## Built on by (most cited first, 30 of 36)

- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Large-Scale Differentially Private BERT](https://mlsanity.com/paper/2108.01624/) (2021)
- [Public Data-Assisted Mirror Descent for Private Model Training](https://mlsanity.com/paper/2112.00193/) (2021)
- [(Amplified) Banded Matrix Factorization: A unified approach to private training](https://mlsanity.com/paper/2306.08153/) (2023)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [CrowdGuard: Federated Backdoor Detection in Federated Learning](https://mlsanity.com/paper/2210.07714/) (2022)
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024)
- [DP-MLM: Differentially Private Text Rewriting Using Masked Language Models](https://mlsanity.com/paper/2407.00637/) (2024)
- [BayBFed: Bayesian Backdoor Defense for Federated Learning](https://mlsanity.com/paper/2301.09508/) (2023)
- [Applications of Federated Learning in Smart Cities: Recent Advances, Taxonomy, and Open Challenges](https://mlsanity.com/paper/2102.01375/) (2021)
- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [Towards Causal Federated Learning For Enhanced Robustness and Privacy](https://mlsanity.com/paper/2104.06557/) (2021)
- [A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directions](https://mlsanity.com/paper/2406.03820/) (2024)
- [Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis](https://mlsanity.com/paper/2410.23131/) (2024)
- [SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)](https://mlsanity.com/paper/2501.06650/) (2025)
- [Hierarchical Federated Learning with Privacy](https://mlsanity.com/paper/2206.05209/) (2022)
- [RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis](https://mlsanity.com/paper/2502.18517/) (2025)
- [Utility Fairness for the Differentially Private Federated Learning](https://mlsanity.com/paper/2109.05267/) (2021)
- [LatticeGen: A Cooperative Framework which Hides Generated Text in a Lattice for Privacy-Aware Generation on Cloud](https://mlsanity.com/paper/2309.17157/) (2023)
- [Privacy-preserving design of graph neural networks with applications to vertical federated learning](https://mlsanity.com/paper/2310.20552/) (2023)
- [Differentially Private Federated Learning: Servers Trustworthiness, Estimation, and Statistical Inference](https://mlsanity.com/paper/2404.16287/) (2024)
- [Federated Learning for Blind Image Super-Resolution](https://mlsanity.com/paper/2404.17670/) (2024)
- [QuanCrypt-FL: Quantized Homomorphic Encryption with Pruning for Secure Federated Learning](https://mlsanity.com/paper/2411.05260/) (2024)
- [Enhancing Privacy in the Early Detection of Sexual Predators Through Federated Learning and Differential Privacy](https://mlsanity.com/paper/2501.12537/) (2025)
- [Model Inversion Attacks on Llama 3: Extracting PII from Large Language Models](https://mlsanity.com/paper/2507.04478/) (2025)
- [Private Cross-Silo Federated Learning for Extracting Vaccine Adverse Event Mentions](https://mlsanity.com/paper/2103.07491/) (2021)
- [Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations](https://mlsanity.com/paper/2306.03600/) (2023)
- [Can large language models be privacy preserving and fair medical coders?](https://mlsanity.com/paper/2412.05533/) (2024)
- [Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions](https://mlsanity.com/paper/2603.23472/) (2026)
- [Statistical Limits and Efficient Algorithms for Differentially Private Federated Learning](https://mlsanity.com/paper/2605.18656/) (2026)

## Abstract (arXiv)

We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our work builds on recent advances in the training of deep networks on user-partitioned data and privacy accounting for stochastic gradient descent. In particular, we add user-level privacy protection to the federated averaging algorithm, which makes "large step" updates from user-level data. Our work demonstrates that given a dataset with a sufficiently large number of users (a requirement easily met by even small internet-scale datasets), achieving differential privacy comes at the cost of increased computation, rather than in decreased utility as in most prior work. We find that our private LSTM language models are quantitatively and qualitatively similar to un-noised models when trained on a large dataset.