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. Differentially Private Language Generation and Identification in the Limit

    Apr 9, 2026Anay Mehrotra, Grigoris Velegkas, Xifan Yu +1Text GenerationDifferential Privacy

    Stanford University · Google Research · Yale University

  2. TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems

    Apr 9, 2026Labani Halder, Payel Sadhukhan, Sarbani PalitPrivacy-Preserving MLDifferential Privacy

    Indian Statistical Institute Kolkata 203 B.T. Road, Kolkata-700108, India · Army Institute of Management Plot No III/B-11, Action Area III, New Town, Kolkata-700160, India

  3. Differentially Private Modeling of Disease Transmission within Human Contact Networks

    Apr 8, 2026Shlomi Hod, Debanuj Nayak, Jason R. Gantenberg +3Differential Privacy

    Department of Computer Science, Boston University · Department of Health Services, Policy & Practice, School of Public Health, Brown University · Department of Epidemiology, School of Public Health, Brown University +1

  4. 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

  5. Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation

    Apr 8, 2026Wenjing Wei, Farid Nait-Abdesselam, Alla JammineAdaptive Aggregation in Federated LearningPrivacy-Preserving Federated Learning

    Université Paris Cité, Paris, France

  6. Optimal Rates for Pure ε\varepsilon-Differentially Private Stochastic Convex Optimization with Heavy Tails

    Apr 7, 2026Andrew LowyHeavy-Tailed Stochastic OptimizationDifferential Privacy

    CISPA Helmholtz Center for Information Security

  7. Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing

    Apr 6, 2026MD Shafikul Islam, Mahathir Mohammad Bappy, Saifur Rahman Tushar +1Privacy-Preserving MLDifferential Privacy

    Mechanical and Industrial Engineering Louisiana State University Baton Rouge, LA 70803 · Department of Computer Science Missouri University of Science and Technology Missouri S&T, Rolla, MO 65409

  8. Communication-Efficient Distributed Learning with Differential Privacy

    Apr 2, 2026Xiaoxing Ren, Yuwen Ma, Nicola Bastianello +3Communication-Efficient Distributed TrainingDifferentially Private Federated Learning

    School of Civil and Environmental Engineering, Cornell University, Ithaca, New York, United States. · Department of Electronic and Electrical Engineering, University College London, London WC1E 7JE, United Kingdom. · School of Electrical Engineering and Computer Science, and Digital Futures, KTH Royal Institute of Technology, Stockholm, Sweden. +4

  9. Differentially Private Manifold Denoising

    Apr 1, 2026Jiaqi Wu, Yiqing Sun, Zhigang YaoPrivacy-Preserving MLDifferential Privacy

    Department of Statistics and Data Science, National University of Singapore

  10. Accurate and Scalable Matrix Mechanisms via Divide and Conquer

    Apr 1, 2026Guanlin He, Yingtai Xiao, Jiamu Bai +4Differential Privacy

    Penn State University · TikTok · Binghamton University

  11. On the Optimal Number of Grids for Differentially Private Non-Interactive KK-Means Clustering

    Mar 27, 2026Gokularam Muthukrishnan, Anshoo TandonPrivacy-Preserving MLDifferential Privacy

    The authors are with the Center of Data for Public Good, Foundation for Science Innovation and Development, Indian Institute of Science, Bengaluru 560012, India

  12. Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms

    Mar 27, 2026Ayaka Sakata, Haruka TanzawaApproximate Message PassingPrivacy-Preserving ML

    Department of Information Science, Ochanomizu University · RIKEN center for AIP

  13. Amplified Patch-Level Differential Privacy for Free via Random Cropping

    Mar 25, 2026Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt +1Personalized Differential PrivacyPrivacy-Preserving ML

    Technical University of Munich · Machine Learning Research, Morgan Stanley

  14. Federated fairness-aware classification under differential privacy

    Mar 25, 2026Gengyu Xue, Yi YuAlgorithmic FairnessDifferentially Private Federated Learning

    Department of Statistics, University of Warwick

  15. Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy

    Mar 24, 2026Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu +2Differential PrivacyPrivacy Auditing

    School of Computing, FSE, Macquarie University, Sydney, Australia

  16. Combinatorial Privacy: Private Multi-Party Bitstream Grand Sum by Hiding in Birkhoff Polytopes

    Mar 24, 2026Praneeth VepakommaSecure Multi-Party ComputationSecure Aggregation

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Massachusetts Institute of Technology (MIT)

  17. Adversarial Attacks on Locally Private Graph Neural Networks

    Mar 21, 2026Matta Varun, Ajay Kumar Dhakar, Yuan Hong +1Adversarial AttacksGraph Neural Networks

    Indian Institute of Technology Kharagpur, India · University of Connecticut, USA

  18. Minimax and Adaptive Covariance Matrix Estimation under Differential Privacy

    Mar 20, 2026T. Tony Cai, Yicheng LiCovariance EstimationParameter Estimation

    Department of Statistics and Data Science, The Wharton School, University of Pennsylvania · KLATASDS-MOE, School of Statistics, East China Normal University

  19. When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence

    Mar 19, 2026Chen Yaoling, Liang Hao, Tu XiaotongPrivacy AccountingDifferentially Private Federated Learning

    School of Informatics, Xiamen University, China · Internet of Things Thrust, Hong Kong University of Science and Technology (Guangzhou), China

  20. Computation-Utility-Privacy Tradeoffs in Bayesian Estimation

    Mar 18, 2026Sitan Chen, Jingqiu Ding, Mahbod Majid +1Differential PrivacyBayesian Inference

    Harvard · ETH Zurich · MIT

  21. 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

  22. Federated Learning for Privacy-Preserving Medical AI

    Mar 16, 2026Tin HoangDifferentially Private Federated LearningDifferential Privacy

    School of Computer Science and Electrical and Electronic Engineering, Faculty of Engineering and Physical Sciences, University of Surrey, Guildford, Surrey, GU2 7XH, UK

  23. DPxFin: Adaptive Differential Privacy for Anti-Money Laundering Detection via Reputation-Weighted Federated Learning

    Mar 14, 2026Renuga Kanagavelu, Manjil Nepal, Ning Peiyan +6Anti-Money Laundering DetectionDifferentially Private Federated Learning

    A*STAR IHPC Singapore · SRM University-AP Andhra Pradesh, India · EVYD Singapore

  24. REAEDP: Entropy-Calibrated Differentially Private Data Release with Formal Guarantees and Attack-Based Evaluation

    Mar 14, 2026Bo Ma, Jinsong Wu, Wei Qi YanDifferentially Private Synthetic Data GenerationDifferential Privacy

    School of Mathematics and Computer Engineering, Auckland University of Technology, Auckland 1024 New Zealand · Resideo Technologies, Inc., Austin, TX 78759, USA · Department of Artificial Intelligence, Guilin University of Electronic Technology, Gui Lin, China +1

  25. TSDCRF: Balancing Privacy and Multi-Object Tracking via Time-Series CRF and Normalized Control Penalty

    Mar 14, 2026Bo Ma, Jinsong Wu, Weiqi YanMulti-Object TrackingDifferential Privacy

    School of Mathematics and Computer Engineering, Auckland University of Technology,Auckland 1024, New Zealand · Department of Electrical Engineering, University of Chile, Santiago, Chile

  26. Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap

    Mar 13, 2026Zakia Zaman, Praveen Gauravaram, Mahbub Hassan +2Privacy-Preserving MLInternet of Things

    School of CSE, University of NSW, AU · TCS Research & Innovation, Tata Consultancy Services (Australia & New Zealand), Australia

  27. Preventing overfitting in deep learning using differential privacy

    Mar 12, 2026Alizishaan Anwar Hussein KhatriNeural Network GeneralizationDifferential Privacy

    Faculty of the Graduate School of University at Buffalo, State University of New York; Department of Computer Science and Engineering

  28. STAMP: Selective Task-Aware Mechanism for Text Privacy

    Mar 12, 2026Fengwei Tian, Payel Bhattacharjee, Heidi Hanson +3Privacy-Utility TradeoffPrivacy-Preserving Language Models

    University of Arizona · Oak Ridge National Laboratory · Duke University

  29. Denoising the US Census: Succinct Block Hierarchical Regression

    Mar 10, 2026Badih Ghazi, Pritish Kamath, Ravi Kumar +2Linear RegressionDifferential Privacy

    Google Research

  30. Nonparametric Variational Differential Privacy via Embedding Parameter Clipping

    Mar 10, 2026Dina El Zein, Shashi Kumar, James HendersonRényi Differential PrivacyPrivacy-Preserving Language Models

    Idiap Research Institute, Switzerland · EPFL, Switzerland