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

314 papers39 papers in the last four weeks, up 5% on the four weeks before. 0.3% of all new papers.

  1. Ask in the Crowd: Differentially Private LLM Inference via Dummy-Augmented Shuffling

    Nov 19, 2026Zhihao Liu, Zixiong Guo, Shuo Shao +5Privacy-Preserving Language ModelsDifferential Privacy

  2. Differentially Private Score Estimation with Applications to Score-Based Generative Models

    Nov 19, 2026Mengxiao Gao, Elly K. H. Hung, Yuchen Wu +1Differential PrivacyScore-Based Generative Modeling

  3. PriTabICL: Differentially Private Tabular In-Context Learning with Task-Aligned Cluster-Wise Synthesis

    Nov 18, 2026Syed Ahzaz Shah, Evan Bramblett, Héber H. Arcolezi +3Differentially Private Synthetic Data GenerationTabular ICL

  4. Privacy-Preserving Clustering Algorithm and Parameter Selection for Collaborative Population Stratification Using Distributed PCA

    Nov 13, 2026Maryam Ghasemian, Lynette Hammond Gerido, Erman AydayPrivacy-Preserving MLClustering

  5. Quantifying Membership Inference Risks in Genomic Data Sharing: The Role of Attacker's Auxiliary Information

    Nov 13, 2026Maryam Ghasemian, Lynette Hammond Gerido, Erman AydayMembership Inference AttacksPrivacy Auditing

  6. MammothDP: Private Boosted Decision Trees Ready for Trusted Hardware and Leakage-free Hyperparameters

    Nov 10, 2026Moritz Kirschte, Thorsten Peinemann, Kari Kostiainen +3Privacy-Preserving MLGradient-Boosted Decision Trees

  7. Optimal Rates for Adaptive Private kk-PCA

    Nov 9, 2026Johanna Düngler, Amartya SanyalPrincipal Component AnalysisDifferential Privacy

  8. Differentially Private GraphRAG: Protecting Relation Connectivity and Semantics

    Nov 6, 2026Jie Fu, Yuan Hong, Yue Ning +1Privacy-Preserving RAGGraph Retrieval-Augmented Generation

  9. On Differentially Private Mechanisms for Linear Regression

    Nov 5, 2026Bardiya Aryanfard, Monika Henzinger, Farhood RostamkhaniLinear RegressionDifferential Privacy

  10. Statistical and Privacy Guarantees for Deep M-Regression via Stochastic Gradient Langevin Dynamics

    Nov 5, 2026Yeheng Ge, Jian Huang, Shuyuan WuStochastic Gradient Langevin DynamicsNonparametric Regression

  11. Dimension-Free Private Mean Estimation is Impossible Without the Covariance

    Nov 4, 2026Renaud Gaucher, Ephraim Linder, Adam Smith +2Differential PrivacyMinimax Estimation

  12. Privacy for Free in Efficient Agnostic Halfspace Learning

    Nov 3, 2026Giorgio Racca, Amartya Sanyal, Vikrant SinghalHalfspace LearningAgnostic Learning

  13. Should We Combine Our Data? Algorithms and Limits for Privately Assessing Data Sharing

    Nov 2, 2026Mahdi Haghifam, Kumar Kshitij Patel, Avrim Blum +2Privacy-Preserving MLStatistical Learning Theory

  14. Infinite Quantiles Inference under Local Differential Privacy

    Oct 31, 2026Yi Liu, Qirui HuConfidence Region EstimationDifferential Privacy

  15. Private Uniform Language Generation

    Oct 31, 2026Di Wang, Peng YeDifferential Privacy

  16. New Lower Bounds for Private PAC Learning

    Oct 30, 2026Prathamesh Dharangutte, Amartya SanyalPAC LearningDifferential Privacy

  17. Communication-Efficient Private Federated Reinforcement Learning with Post-Quantum Authentication for Vehicular Networks

    Oct 29, 2026Hojat Allah Salehi, Devrim Aras, Md Jueal Mia +4Vehicular NetworksFederated RL

  18. Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering

    Oct 29, 2026Moshe Shenfeld, Eliad Tsfadia, Katrina LigettDifferential Privacy

  19. Privately Clipping Heavy-Tailed Data

    Oct 26, 2026Matthew Joseph, Alex KuleszaDifferential PrivacyHeavy-Tailed Distributions

  20. Projection-Based Federated Learning on Compact Submanifolds with Geometry-Independent Differential Privacy

    Oct 24, 2026Thibault Pautrel, Florent Bouchard, Guillaume Ginolhac +2Differentially Private Federated LearningFederated Learning