Privacy-Preserving Language Models

Ask about this topic

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

179 papers26 papers in the last four weeks, up 8% on the four weeks before. 0.2% of all new papers.

  1. Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition

    Apr 25, 2026Rujing Yao, Yufei Shi, Yang Wu +5Privacy-Preserving Language ModelsKnowledge Augmentation for Language Models

    1Nankai University, China · 2The Hong Kong Polytechnic University, China · 3Worcester Polytechnic Institute, USA +3

  2. UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

    Apr 25, 2026Tianlong Yu, Yang Yang, Xiao Luo +6Privacy-Preserving Language ModelsLLM Guardrails

    Hubei University, Wuhan, China · University of Southern California, Los Angeles, USA · Huazhong University of Science and Technology, Wuhan, China

  3. Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies

    Apr 23, 2026Chris Schneider, Philipp Schoenegger, Ben BariachLLM PersonalizationPrivacy-Preserving Language Models

    Microsoft AI

  4. Reinforcing privacy reasoning in LLMs via normative simulacra from fiction

    Apr 21, 2026Matt Franchi, Madiha Zahrah Choksi, Harold Triedman +1Contextual IntegrityPrivacy-Preserving Language Models

    Cornell Tech New York, NY 10044, USA

  5. FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion

    Apr 21, 2026Tao Fan, Guoqiang Ma, Yuanfeng Song +3Privacy-Preserving Language ModelsLLM Fine-Tuning

    Hong Kong University of Science and Technology, Hong Kong, China · WeBank Co., Ltd, Shenzhen, China · Hong Kong Polytechnic University, Hong Kong, China

  6. Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support

    Apr 20, 2026Eranga Bandara, Asanga Gunaratna, Ross Gore +9On-Device Language Model InferencePrivacy-Preserving Language Models

    Old Dominion University, Norfolk, VA, USA · AI Motion Labs, Melbourne, Australia · Department of Psychiatry and Neurobehavioral Sciences, University of Virginia School of Medicine, Charlottesville, VA, USA +3

  7. If Only My CGM Could Speak: A Privacy-Preserving Agent for Question Answering over Continuous Glucose Data

    Apr 18, 2026Yanjun Cui, Ali Emami, Temiloluwa Prioleau +1Privacy-Preserving Language ModelsHealthcare

    Dartmouth College · Emory University

  8. FedLLM: A Privacy-Preserving Federated Large Language Model for Explainable Traffic Flow Prediction

    Apr 17, 2026Seerat Kaur, Sukhjit Singh Sehra, Dariush EbrahimiPrivacy-Preserving Language ModelsTraffic Flow Estimation

    Department of Physics & Computer Science, Wilfrid Laurier University, Waterloo, Canada

  9. SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models

    Apr 17, 2026Noor Islam S. Mohammad, Uluğ BayazıtLLM Hallucination MitigationPrivacy-Preserving Language Models

    Istanbul Technical University

  10. Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation

    Apr 16, 2026Yisheng Zhong, Sijia Liu, Zhuangdi ZhuPrivacy-Preserving Language ModelsLLM Unlearning

    George Mason University · Michigan State University

  11. CURaTE: Continual Unlearning in Real Time with Ensured Preservation of LLM Knowledge

    Apr 16, 2026Seyun Bae, Seokhan Lee, Eunho YangPrivacy-Preserving Language ModelsFactual Knowledge in Language Models

    1KT Corporation · 2KAIST

  12. CAMP: Cumulative Agentic Masking and Pruning for Privacy Protection in Multi-Turn LLM Conversations

    Apr 16, 2026Aman PanjwaniPrivacy-Preserving Language ModelsPrivacy Leakage in Language Models

    Independent Researcher

  13. Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments

    Apr 14, 2026Esen Kurt, Haithem AfliLLM UnlearningMachine Unlearning

    Department of Mathematics Munster Technological University · Department of Computer Science Munster Technological University

  14. Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference

    Apr 14, 2026Anes Abdennebi, Nadjia Kara, Laaziz LahlouPrivacy-Preserving Language ModelsLLM Inference

    Software and IT Engineering Department, École de Technologie Supérieure, Montreal, Quebec, Canada.

  15. Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

    Apr 13, 2026Hanqi Xiao, Vaidehi Patil, Zaid Khan +3Theory of MindAI Agent Safety

    UNC Chapel Hill · University of Texas at Austin

  16. Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation

    Apr 8, 2026Qian Ma, Sarah RajtmajerPrivacy-Preserving Language ModelsSynthetic Data Generation

    Information Sciences and Technology, The Pennsylvania State University

  17. On the Price of Privacy for Language Identification and Generation

    Apr 8, 2026Xiaoyu Li, Andi Han, Jiaojiao Jiang +1Privacy-Preserving Language ModelsLanguage Identification

    University of New South Wales · University of Sydney

  18. Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation

    Apr 8, 2026Jeongho Yoon, Chanhee Park, Yongchan Chun +2Privacy-Preserving Language ModelsPrivacy-Preserving ML

    Department of Computer Science and Engineering, Korea University · Samsung Mobile eXperience Business

  19. Say Something Else: Rethinking Contextual Privacy as Information Sufficiency

    Apr 7, 2026Yunze Xiao, Wenkai Li, Xiaoyuan Wu +3Privacy-Preserving Language ModelsPrivacy Protection for LLM Agents

    Carnegie Mellon University · Massachusetts Institute of Technology · 2077AI +1

  20. BodhiPromptShield: Pre-Inference Prompt Mediation for Surface-Form Privacy Propagation in LLM Agent Pipelines

    Apr 7, 2026Bo Ma, Jinsong Wu, Weiqi YanData LeakagePrivacy-Preserving Language Models

    Auckland University of Technology Auckland, New Zealand · Guilin University of Electronic Technology Guilin, China

  21. DP-OPD: Differentially Private On-Policy Distillation for Language Models

    Apr 6, 2026Fatemeh Khadem, Sajad Mousavi, Yi Fang +1Privacy-Preserving Language ModelsPrivacy-Preserving ML

    Santa Clara University, Santa Clara, California, USA · Independent Researcher

  22. CARE: Privacy-Compliant Agentic Reasoning with Evidence Discordance

    Apr 1, 2026Haochen Liu, Weien Li, Rui Song +6Privacy-Preserving Language ModelsHealthcare

    University of Cambridge · McGill University · MBZUAI - Mohamed bin Zayed University of Artificial Intelligence +2

  23. Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents

    Apr 1, 2026Dayong Ye, Tainqing Zhu, Congcong Zhu +5LLM UnlearningPrivacy-Preserving Language Models

  24. Privacy Guard & Token Parsimony by Prompt and Context Handling and LLM Routing

    Mar 30, 2026Alessio LangiuPrivacy Protection for LLM AgentsPrivacy Leakage in Language Models

    National Research Council of Italy - Institute of Marine Sciences (CNR-ISMAR)

  25. Supercharging Federated Intelligence Retrieval

    Mar 26, 2026Dimitris Stripelis, Patrick Foley, Mohammad Naseri +4Privacy-Preserving RAGRetrieval-Augmented Generation

    Flower Labs

  26. PLACID: Privacy-preserving Large language models for Acronym Clinical Inference and Disambiguation

    Mar 24, 2026Manjushree B. Aithal, Ph. D., Alexander Kotz +2Clinical NLPPrivacy-Preserving Language Models

    Department of Biomedical Informatics, University of Colorado Anschutz, Aurora, CO

  27. Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling

    Mar 23, 2026Young Hyun Cho, Will Wei SunPrivacy-Preserving MLPrivacy-Preserving Language Models

    Purdue University

  28. Differential Privacy in Generative AI Agents: Analysis and Optimal Tradeoffs

    Mar 18, 2026Ya-Ting Yang, Quanyan ZhuPrivacy Leakage in Language ModelsPrivacy-Preserving Language Models

    Department of Electrical and Computer Engineering, New York University, NY, 11201, USA

  29. Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text

    Mar 17, 2026Federico Albanese, Pablo Ronco, Nicolás D'IppolitoPrivacy-Preserving MLPrivacy-Preserving Language Models

    Veritran, Buenos Aires, Argentina · University of Buenos Aires, Argentina · University of San Andrés, Buenos Aires, Argentina

  30. SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized Generation

    Mar 17, 2026Hang Lv, Sheng Liang, Hao Wang +6Personalized Language ModelsOn-Device Language Model Inference

    University of Science and Technology of China · Huawei Technologies Co., Ltd.