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. On the Limits of Sparse Linear Model with Shuffled Differential Privacy

    Oct 23, 2026Yan Zhang, Jiong Tuo, Meng Ding +2High-Dimensional Linear RegressionDifferential Privacy

  2. Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy

    Oct 22, 2026Gautam Kamath, Mahbod Majid, Ankur Moitra +2Robust StatisticsDifferential Privacy

  3. Differentially Private Sparse Reward Estimation with Preference Feedback

    Oct 21, 2026Meng Ding, Mingxi Lei, Jie Zhang +2Reward ModelingRL from Human Feedback

  4. Private Online Prediction from Experts with Small Losses

    Oct 21, 2026Bo Li, Peng YePrivacy-Preserving MLDifferential Privacy

  5. Differentially Private Synthetic Data via Generalized Moment Matching

    Oct 21, 2026Rundong Ding, Yiyun He, Yizhe ZhuDifferentially Private Synthetic Data GenerationDifferential Privacy

  6. Unit-Aware Differentially Private Quantum Machine Learning for Clinical and Wearable Health Data

    Oct 20, 2026Md Khalid Syfullah, Alvi Ataur KhalilPrivacy-Preserving MLQuantum Machine Learning

  7. Actually, All Learnable Distribution Classes Are Privately Learnable

    Oct 20, 2026Mohammad Afzali, Hassan Ashtiani, Alex Bie +4Differential PrivacyStatistical Learning Theory

  8. CALLIOPE: Private Insights into AI Use, Without Embeddings

    Oct 20, 2026Edith Cohen, Vadym Doroshenko, Badih Ghazi +11Topic ModelingPrivacy-Preserving ML

  9. Privacy Accounting for Empirical Denoisers

    Oct 20, 2026William Cheng, Dongjun Kim, Mijung ParkDifferential PrivacyDiffusion Sampling

  10. Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference

    Oct 19, 2026Mingchen Li, Zifan Peng, Kewei Sha +5Privacy-Preserving Language ModelsDifferential Privacy

  11. BR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic Analytics

    Oct 19, 2026Abdolazim RezaeiPrivacy-Preserving MLDifferential Privacy

  12. Reliable Estimation of Differential Privacy under Selection Bias

    Oct 19, 2026Valentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif +2Privacy AuditingDifferential Privacy

  13. Private Evaluation of High-Dimensional Functions

    Oct 17, 2026Mohammad Afzali, Hassan Ashtiani, Adam SmithDifferential PrivacyBlack-Box Optimization

  14. Task-aware Kernel Stein certificates for Rényi differential privacy

    Oct 16, 2026Leoni Carla Wirth, Tara Trauthwein, Gesine ReinertKernel Stein DiscrepancyRényi Differential Privacy

  15. Nearly Linear Private Learning of Littlestone Classes

    Oct 16, 2026Shay Moran, Chao YanDifferential PrivacyPAC Learning

  16. Spectrum Is Not Enough: A Random-Matrix Account of Data-Free Preconditioning for Differentially Private Learning

    Oct 15, 2026Shilin Zhang, Kangning WangKronecker-Factored ApproximationDifferential Privacy

  17. SHIP: Structured and Hierarchical Insight with Privacy

    Oct 15, 2026Kai Chen, Guisi Ni, Albert Cheu +4Differentially Private Synthetic Data GenerationPrivacy-Utility Tradeoff

  18. Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy

    Oct 15, 2026Mohammad Afzali, Hassan Ashtiani, Sivan SabatoDifferential PrivacyDensity Estimation

  19. On Inherent Privacy of Posterior Sampling: A Unified Rényi-Divergence Framework

    Oct 14, 2026Ruyu Zhou, Fang LiuRényi Differential PrivacyPosterior Sampling

  20. Rank-Aware Differentially Private Release of Listwise Preferences for LLM Alignment

    Oct 13, 2026Junwei Chen, Manjiang Yu, Pengpeng Qiao +1Privacy-Preserving Language ModelsDifferential Privacy

  21. Can Rényi Accountants Beat Lossless Accountants for DP-SGD?

    Oct 12, 2026Jinho BokPrivacy AccountingRényi Differential Privacy

  22. DP-MIND: Differentially private memory-guided Long context Inference

    Oct 9, 2026Zhihao Liu, Yitian Cheng, Shuang Liu +3Privacy-Preserving Language ModelsLong-Context Language Model Inference

  23. BRACE: Differential Privacy for Dense Associative Memory with LSR Energy

    Oct 8, 2026Chang Qu, Zhaoyang ShiAssociative MemoryDifferential Privacy

  24. Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series Forecasting

    Oct 7, 2026Guoxiong Long, Huizhen Huang, Qikun Cai +2Synthetic Data EvaluationSynthetic Data Generation

  25. Efficient Provably Private Classification with a Tabular Foundation Model

    Oct 7, 2026Talal Alrawajfeh, Cristiana Diaconu, Ossi Räisä +5Privacy-Preserving MLTabular Foundation Models