Privacy-Preserving Language Models

Overview

This field studies how to use and adapt language models without exposing private training data, user prompts, or personal context. Approaches include differential privacy for fine-tuning and preference alignment, federated and split learning, cryptographic inference, and practical safeguards such as on-device processing, prompt sanitization, and selective unlearning. Researchers evaluate both formal guarantees and empirical attacks, including membership inference, data extraction, and reconstruction from intermediate activations, across language tasks and clinical or conversational settings. The central tension is preserving privacy without sacrificing model quality, cost, or speed, while ensuring evaluations reflect realistic, multi-turn use and adaptive attackers.

Latest papers

CardsList

191 papers16 papers in the last four weeks, down 41% on the four weeks before. 0.1% of all new papers.

  1. RUVA: Personalized Transparent On-Device Graph Reasoning

    Feb 17, 2026Gabriele Conte, Alessio Mattiace, Gianni Carmosino +6Human-in-the-Loop AIPrivacy-Preserving Language Models

  2. AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs

    Jan 30, 2026Jaehee Kim, Pilsung KangPrivacy-Preserving Language ModelsPrivacy Leakage in Language Models

  3. VoxPrivacy: A Benchmark for Evaluating Interactional Privacy of Speech Language Models

    Jan 27, 2026Yuxiang Wang, Hongyu Liu, Dekun Chen +2Privacy-Preserving Language ModelsLanguage Model Safety Evaluation

  4. Improved Bounds for Private and Robust Alignment

    Dec 29, 2025Wenqian Weng, Yi He, Xingyu ZhouPrivacy-Preserving Language ModelsCorruption Robustness

  5. User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

    Oct 23, 2025Xiaoyuan Wu, Roshni Kaushik, Wenkai Li +2LLM EvaluationLLM-as-a-Judge

  6. Protecting De-identified Documents from Search-based Linkage Attacks

    Oct 7, 2025Pierre Lison, Mark AndersonPrivacy-Preserving Language Models

  7. Re-examining low-rank adaptation for private LLM fine-tuning

    Oct 1, 2025Ali Dadsetan, Frank RudziczPrivacy-Preserving Language ModelsLow-Rank Adaptation

  8. SynBench: A Benchmark for Differentially Private Text Generation

    Sep 18, 2025Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +9Differentially Private Synthetic Data GenerationPrivacy-Preserving Language Models

  9. Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training

    Jul 2, 2025Ismail Labiad, Mathurin Videau, Matthieu Kowalski +4Privacy-Preserving Language ModelsEvolutionary Optimization

  10. Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks

    Apr 24, 2025Yang Liu, Kejia Zhang, Bingjie Yan +11Privacy-Preserving Language ModelsLLM Fine-Tuning

  11. When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

    Oct 20, 2024Shang Wang, Tianqing Zhu, Dayong Ye +1Privacy-Preserving Language ModelsLLM Unlearning