Differential Privacy Papers

Privately Clipping Heavy-Tailed Data Matthew Joseph, Alex Kulesza http://arxiv.org/abs/2610.36281

Differentially Private Preconditioned Power Iteration Method for Principal Component Analysis that Adapts to the Coherence Duy V. Le, Ta Duy Nguyen, Alina Ene, Huy L. Nguyen http://arxiv.org/abs/2610.36691

Gaussian Approximation for Composition and Subsampling of Differentially Private Algorithms Vitaly Feldman, Moshe Shenfeld http://arxiv.org/abs/2610.33333

Projection-Based Federated Learning on Compact Submanifolds with Geometry-Independent Differential Privacy Thibault Pautrel, Florent Bouchard, Guillaume Ginolhac, Ammar Mian, Aurélien Bellet http://arxiv.org/abs/2610.33712

PRISMA: Differentially Private Synthetic In-Car Telemetry via Differentiable Simulation Kilian Zeiseweis, Nele Sophie Brügge, Marven Kummerfeldt, Ali Raza, Esfandiar Mohammadi http://arxiv.org/abs/2610.35521

Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information Xincheng Xu, Thilina Ranbaduge, Thierry Rakotoarivelo, David Smith http://arxiv.org/abs/2610.32175

On the Limits of Sparse Linear Model with Shuffled Differential Privacy Yan Zhang, Jiong Tuo, Meng Ding, Yuheng Ma, Di Wang http://arxiv.org/abs/2610.32822

Near-Optimal List Replicability from Littlestone Dimension Ari Blondal, Pooya Hatami, Chavdar Lalov, Sivan Tretiak http://arxiv.org/abs/2610.32853

CALLIOPE: Private Insights into AI Use, Without Embeddings Edith Cohen, Vadym Doroshenko, Badih Ghazi, Charlie Harrison, Pritish Kamath, Alexander Knop, Ravi Kumar, Ethan Leeman, Pasin Manurangsi, Mikhail Pravilov, Adam Sealfon, Yurii Sushko, Marika Swanberg, Chiy... http://arxiv.org/abs/2610.28797

Actually, All Learnable Distribution Classes Are Privately Learnable Mohammad Afzali, Hassan Ashtiani, Alex Bie, Gautam Kamath, Peihan Liu, Argyris Mouzakis, Vikrant Singhal http://arxiv.org/abs/2610.28878

Unit-Aware Differentially Private Quantum Machine Learning for Clinical and Wearable Health Data Md Khalid Syfullah, Alvi Ataur Khalil http://arxiv.org/abs/2610.28968

Diffusion Sensitivity Geometry and Strong Duality for Optimal Privacy-Utility Tradeoffs Tue Do, Daniel Alabi http://arxiv.org/abs/2610.28991

Differentially Private Synthetic Data via Generalized Moment Matching Rundong Ding, Yiyun He, Yizhe Zhu http://arxiv.org/abs/2610.30196

Private Online Prediction from Experts with Small Losses Bo Li, Peng Ye http://arxiv.org/abs/2610.29575

Differentially Private Sparse Reward Estimation with Preference Feedback Meng Ding, Mingxi Lei, Jie Zhang, Jinyan Liu, Di Wang http://arxiv.org/abs/2610.30099

Membership Inference Attack on Private Evolution Daniil Filienko, Sikha Pentyala, Martine De Cock http://arxiv.org/abs/2610.30514

Federated Differentially Private Optimization via Low-Rank Preconditioning Antti Koskela, Tejas Kulkarni, Elias Raninen http://arxiv.org/abs/2610.31069

Practical Auditing of Differentially Private Graph Release Mechanisms: Methodology, Toolkit, and Case Study Nicholas D'Silva, Surya Nepal, Salil S. Kanhere http://arxiv.org/abs/2610.31294

Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy Gautam Kamath, Mahbod Majid, Ankur Moitra, Argyris Mouzakis, Jonathan Ullman http://arxiv.org/abs/2610.31612

Reliable Estimation of Differential Privacy under Selection Bias Valentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif, Olivier Cappé, Nicolas Papernot http://arxiv.org/abs/2610.27021

BR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic Analytics Abdolazim Rezaei http://arxiv.org/abs/2610.27026

Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference Mingchen Li, Zifan Peng, Kewei Sha, Lavinia F Pieptea, Heng Fan, Junhua Ding, Meikang Qiu, Yunhe Feng http://arxiv.org/abs/2610.27213

Guided Diffusion for Trustworthy Synthetic Text Generation Qi Pang, Hanshen Xiao, Andre Manoel, Lipika Ramaswamy, Wenting Zheng, Virginia Smith, G. Edward Suh http://arxiv.org/abs/2610.27259

DISTA-LP: Privacy-Preserving Distributed Linear Programming for Metric Differential Privacy Michael Oluwole, Ruiyao Liu, Aleksander Stevens, Chenxi Qiu http://arxiv.org/abs/2610.27615

Privacy Accounting for Empirical Denoisers William Cheng, Mijung Park, Dongjun Kim http://arxiv.org/abs/2610.27710

Lower bounds for Bayesian CVaR in interactive problems with local differential privacy Raghav Bongole, Amirreza Zamani, Tobias J. Oechtering, Mikael Skoglund http://arxiv.org/abs/2610.28153

Private Evaluation of High-Dimensional Functions Mohammad Afzali, Hassan Ashtiani, Adam Smith http://arxiv.org/abs/2610.24477

How Does Muon Work in Private Deep Learning? Scalable Differentially Private Training via Orthogonalization Alexander Gaponov, Grigory Malinovsky, Egor Shulgin, Peter Richtarik http://arxiv.org/abs/2610.24736

Learning Which Device to Call: Online Tool Grounding for LLM Agents in IoT Yichen Liu, Xiaochong Jiang, Haoran Yu, Lifei Liu http://arxiv.org/abs/2610.25563

Formalization of Rényi Differential Privacy in Isabelle/HOL (Draft version) Tetsuya Sato http://arxiv.org/abs/2610.25636

Basis Selection For Analog Coded Computing Under Differential Privacy Constraints Aaditya Sharma, Rimpi Borah, J. Harshan http://arxiv.org/abs/2610.26385

Differential privacy with adjustable preservation of multivariate relationships Nicolas Ruiz http://arxiv.org/abs/2610.26460

Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning Mohamed Shaaban, Mohamed Elmahallawy http://arxiv.org/abs/2610.22792

Towards Hyperparameter Transfer for Differentially Private Optimization Tianze Wang, Zhiqi Bu, Linjun Zhang http://arxiv.org/abs/2610.22976

Nearly Linear Private Learning of Littlestone Classes Shay Moran, Chao Yan http://arxiv.org/abs/2610.23160

Task-aware Kernel Stein certificates for Rényi differential privacy Leoni Carla Wirth, Tara Trautwein, Gesine Reinert http://arxiv.org/abs/2610.23798

Efficient Agnostic Learning of Univariate Densities Under Local Differential Privacy Mohammad Afzali, Hassan Ashtiani, Sivan Sabato http://arxiv.org/abs/2610.21033

SHIP: Structured and Hierarchical Insight with Privacy Kai Chen, Guisi Ni, Albert Cheu, Kassem Fawaz, Yuzheng Hu, Ryan McKenna, Peter Kairouz http://arxiv.org/abs/2610.21048

From One Query to Many: A Critical Survey of Privacy Accounting in RAG Zhiyuan Zhang http://arxiv.org/abs/2610.21245

Spectrum Is Not Enough: A Random-Matrix Account of Data-Free Preconditioning for Differentially Private Learning Shilin Zhang, Kangning Wang http://arxiv.org/abs/2610.21312

Subgraph Counting with Local Node Differential Privacy Sofya Raskhodnikova, Adam Smith, Connor Wagaman, Anatoly Zavyalov http://arxiv.org/abs/2610.22278

Private Retrieval Augmented Generation via Random Projection Dixi Yao, Tahseen Rabbani, Tian Li http://arxiv.org/abs/2610.22297

Differentially Private Learning of Markov Chains: Near-Optimal Sample Complexity for Item and User Level Privacy Devansh Gupta, Cristóbal Guzman, Enayat Ullah http://arxiv.org/abs/2610.19335

On Inherent Privacy of Posterior Sampling: A Unified Rényi-Divergence Framework Ruyu Zhou, Fang Liu http://arxiv.org/abs/2610.19573

De-biased Distribution Estimation for Locally Differential Private Survival Data Yi Xiong, Li-Pang Chen, Liyue Fan http://arxiv.org/abs/2610.14320

Minimax Wasserstein Testing under Differential Privacy Bonwoo Lee, Ilmun Kim, Cheolwoo Park http://arxiv.org/abs/2610.14432

Adaptive Confidence Sets for Nonparametric Density Estimation under Local Differential Privacy Aditya Khan, Thibault Randrianarisoa http://arxiv.org/abs/2610.15982

Risk-aware Road-network Trajectory Synthesis under Local Differential Privacy Hongzhen Xiang, Chenxu Wang, Yumeng Song, Tao Qin, Yushuai Li, Pinghui Wang, Wei Wang http://arxiv.org/abs/2610.16384

Differential Privacy Protected Preference Alignment on Survey Derived Data Xiuyuan Qi, Yi Wang, Wenjie Wang http://arxiv.org/abs/2610.16458

Can Rényi Accountants Beat Lossless Accountants for DP-SGD? Jinho Bok http://arxiv.org/abs/2610.17120