Differential Privacy

Ask about this topic

Overview

Differential privacy studies algorithms whose outputs reveal limited information about any individual record, even when an attacker knows other data. Common approaches add calibrated noise to statistics or clipped gradients, use randomized response for local privacy, or combine privacy with subsampling, shuffling, and secure aggregation. These methods support private statistical estimation, machine learning, federated learning, and synthetic data generation, including for images, tables, and text; evaluation often measures both task utility and membership-inference risk. A central tension is that stronger guarantees can reduce accuracy or increase computational cost, while task-specific structure and tighter privacy accounting may improve the trade-off without resolving all deployment risks.

Latest papers

CardsList

285 papers43 papers in the last four weeks, up 54% on the four weeks before. 0.2% of all new papers.

  1. Beyond Data Splitting: Full-Data Conformal Prediction by Differential Privacy

    Mar 8, 2026Young Hyun Cho, Jordan AwanConformal PredictionDifferential Privacy

    Purdue University · University of Pittsburgh

  2. Differentially Private Multimodal In-Context Learning

    Mar 5, 2026Ivoline C. Ngong, Zarreen Reza, Joseph P. NearPrivacy Protection in VLMsMultimodal ICL

    University of Vermont, Burlington, VT, USA · Independent Researcher

  3. LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing

    Mar 4, 2026Yuanming Cao, Chengqi Li, Wenbo HePrivacy-Preserving MLDifferential Privacy

    McMaster University, Hamilton, Ontario, Canada

  4. Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective

    Mar 3, 2026Enea Monzio Compagnoni, Alessandro Stanghellini, Rustem Islamov +2Differentially Private Stochastic Gradient DescentDifferential Privacy

    University of Basel, Switzerland · University of Zürich, Switzerland

  5. PrivMedChat: End-to-End Differentially Private RLHF for Medical Dialogue Systems

    Mar 3, 2026Sudip BhujelPrivacy-Preserving Language ModelsRL from Human Feedback

    Department of Computer Science, University of Kentucky, Lexington, KY, USA

  6. Noise-Calibrated Inference from Differentially Private Sufficient Statistics in Exponential Families

    Mar 2, 2026Amir Asiaee, Samhita PalExponential FamilyDifferential Privacy

    Department of Biostatistics, Vanderbilt University Medical Center, Nashville, TN, USA

  7. Accurate, private, secure, federated U-statistics with higher degree

    Mar 2, 2026Quentin Sinh, Jan RamonU-StatisticsDifferentially Private Federated Learning

    MAGNET · MAGNET, Univ. Lille, INRIA, CNRS, UMR 9189 - CRIStAL, F-59000 Lille, France.

  8. Differential privacy representation geometry for medical image analysis

    Mar 1, 2026Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung +1Neural Representation GeometryHealthcare

    Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany · INDA Institute, RWTH Aachen University, Aachen, Germany

  9. Challenges in Enabling Private Data Valuation

    Feb 27, 2026Yiwei Fu, Tianhao Wang, Varun ChandrasekaranData ValuationPrivacy-Utility Tradeoff

    University of Illinois Urbana-Champaign · ∗University of Virginia

  10. Decomposing Private Image Generation via Coarse-to-Fine Wavelet Modeling

    Feb 26, 2026Jasmine Bayrooti, Weiwei Kong, Natalia Ponomareva +3Image GenerationDifferential Privacy

    University of Cambridge

  11. MAPLE: Metadata Augmented Private Language Evolution

    Feb 26, 2026Eli Chien, Yuzheng Hu, Ryan McKenna +3Privacy-Preserving Language ModelsDifferentially Private Synthetic Data Generation

    National Taiwan University · University of Illinois Urbana-Champaign · Google Research +1

  12. DPSQL+: A Differentially Private SQL Library with a Minimum Frequency Rule

    Feb 26, 2026Tomoya Matsumoto, Shokichi Takakura, Shun Takagi +1Differential PrivacyRelational Databases

    LY Corporation

  13. Tackling Privacy Heterogeneity in Differentially Private Federated Learning

    Feb 26, 2026Ruichen Xu, Ying-Jun Angela Zhang, Jianwei HuangDifferentially Private Federated LearningClient Selection in Federated Learning

    Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong · School of Science and Engineering, Shenzhen Institute of Artificial Intelligence and Robotics for Society, Shenzhen Key Laboratory of Crowd Intelligence Empowered Low-Carbon Energy Network, and CSIJRI Joint Research Centre on Smart Energy Storage, The Chinese University of Hong Kong, Shenzhen, Guangdong, 518172, P.R. China

  14. Differentially Private Truncation of Unbounded Data via Public Second Moments

    Feb 25, 2026Zilong Cao, Xuan Bi, Hai ZhangPrivacy-Preserving MLDifferential Privacy

    School of Mathematics, Northwest University · Department of Information and Decision Sciences, Minnesota Carlson, University of Minnesota

  15. SLDP: Semi-Local Differential Privacy for Density-Adaptive Analytics

    Feb 21, 2026Alexey Kroshnin, Alexandra SuvorikovaDifferential PrivacyPrivacy-Preserving ML

    Weierstrass Institute for Applied Analysis and Stochastic

  16. PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems

    Feb 21, 2026Nnaemeka Obiefuna, Samuel Oyeneye, Similoluwa Odunaiya +2Privacy-Preserving MLDifferential Privacy

    1ML Collective · 2Friedrich-Alexander-Universität Erlangen-Nürnberg · 3Carnegie Mellon University

  17. DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning

    Feb 20, 2026Fangyuan Xu, Sihao Chen, Zinan Lin +13Differentially Private Synthetic Data GenerationSynthetic Data Generation for Language Models

    New York University · Microsoft · University of Southern California

  18. JAX-Privacy: A library for differentially private machine learning

    Feb 19, 2026Ryan McKenna, Galen Andrew, Borja Balle +6Privacy-Preserving MLDifferential Privacy

  19. Efficient privacy loss accounting for subsampling and random allocation

    Feb 19, 2026Vitaly Feldman, Moshe ShenfeldPrivacy AccountingDifferential Privacy

    Apple · The Hebrew University of Jerusalem · *Work partially done while author was an intern at Apple.

  20. Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent

    Feb 18, 2026Jean Dufraiche, Paul Mangold, Michaël Perrot +1Differential PrivacyDifferentially Private Stochastic Gradient Descent

    Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 - CRIStAL, F-59000 Lille, France · CMAP, CNRS, École polytechnique, Institut Polytechnique de Paris, 91120 Palaiseau, France

  21. Differentially Private Non-convex Distributionally Robust Optimization

    Feb 18, 2026Difei Xu, Meng Ding, Zebin Ma +4Distributionally Robust OptimizationDifferential Privacy

    Provable Responsible AI and Data Analytics (PRADA) Lab · King Abdullah University of Science and Technology · State University of New York at Buffalo +1

  22. Certified Per-Instance Unlearning Using Individual Sensitivity Bounds

    Feb 17, 2026Hanna Benarroch, Jamal Atif, Olivier CappéPersonalized Differential PrivacyMachine Unlearning

    DI-ENS · CMAP

  23. Differentially Private Retrieval-Augmented Generation

    Feb 16, 2026Tingting Tang, James Flemings, Yongqin Wang +1Privacy-Preserving RAGRetrieval-Augmented Generation

    University of Southern California Los Angeles, California, USA

  24. Locally Private Parametric Methods for Change-Point Detection

    Feb 14, 2026Anuj Kumar Yadav, Cemre Cadir, Yanina Y. Shkel +1Change-Point DetectionDifferential Privacy

    School of Computer and Communication Sciences, École Polytechnique Fédérale de Lausanne (EPFL), Vaud, Switzerland.

  25. On the Inherent Privacy Amplification of Missing Data

    Feb 2, 2026Simon Roburin, Rafa{ë}l Pinot, Erwan ScornetPrivacy-Preserving MLDifferential Privacy

    LPSM · Sorbonne Université, Université Paris Cité, CNRS Laboratoire de Probabilités, Statistique et Modélisation (LPSM) F-75005 Paris, France

  26. The pretraining domain outweighs the training objective in setting the privacy-utility trade-off of differentially private medical image analysis

    Jan 27, 2026Soroosh Tayebi Arasteh, Mina Farajiamiri, Mahshad Lotfinia +7Privacy-Utility TradeoffMedical Image Classification

    Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany · Department of Urology, Stanford University, Stanford, CA, USA +5

  27. Improved Bounds for Private and Robust Alignment

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

    Department of Electrical and Computer Engineering, Wayne State University, Detroit, USA.

  28. Efficient Public Verification of Private ML via Regularization

    Dec 3, 2025Zoë Ruha Bell, Anvith Thudi, Olive Franzese-McLaughlin +2Differential Privacy

    Department of Computer Science, University of California, Berkeley, USA · Department of Computer Science, University of Toronto, Toronto, Canada · Vector Institute, Toronto, Canada

  29. On the Gradient Complexity of Private Optimization with Private Oracles

    Nov 17, 2025Michael Menart, Aleksandar NikolovQuery ComplexityOracle Complexity

    Department of Computer Science, University of Toronto, Vector Institute · Department of Computer Science, University of Toronto

  30. Beyond One-Size-Fits-All: Neural Networks for Differentially Private Tabular Data Synthesis

    Nov 17, 2025Kai Chen, Chen Gong, Tianhao WangSynthetic Data GenerationSynthetic Tabular Data Generation

    University of Virginia Charlottesville, USA