Differential Privacy

Follow this topic Ask about this topic

Latest papers 193

30 papers in the last four weeks, up 100% on the four weeks before. 0.2% of all new papers.

All topics

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run
May 26, 2026Mathieu Dagréou, Aurélien BelletPrivacy Auditing Membership Inference Attacks
PreMeDICaL team, Inria · Idesp, Inserm, Univ. de Montpellier
PATE-TabTransGAN: Differentially Private Synthetic Tabular Data Generation via Transformer-Based Student Discrimination
May 26, 2026M. Youssef, M. WoźniakSynthetic Tabular Data Generation Differential Privacy
Wrocław University of Science and Technology, Wrocław, Poland
From Privacy to Generalization: Linear Max-Information Bounds for Differentially Private Learning Algorithms
May 25, 2026Christoph H. Lampert, Max Cairney-Leeming, Hossein ZakeriniaPAC-Bayesian Generalization Bounds Differentially Private Stochastic Gradient Descent
Institute of Science and Technology Austria (ISTA) Klosterneuburg, Austria
Private Adaptive Covariance Estimation via Gaussian Graphical Models
May 22, 2026Cecilia Ferrando, Miguel Fuentes, Brett Mullins +2Differential Privacy Covariance Estimation
Manning College of Information and Computer Sciences University of Massachusetts Amherst
On the Stability of Spherical Hellinger-Kantorovich Flows and Their Implications for Differential Privacy
May 22, 2026Aratrika Mustafi, Soumya MukherjeeLangevin Dynamics Differential Privacy
Department of Statistics, Pennsylvania State University
Hidden-State Privacy Has an Empty Middle
May 21, 2026Alexander Okezue BellPrivacy-Preserving Language Models Adversarial Attacks
Stanford University 450 Jane Stanford Way Stanford, CA 94305
Lumberjack: Better Differentially Private Random Forests through Heavy Hitter Detection in Trees
May 21, 2026Christian Janos Lebeda, David Erb, Tudor Cebere +1Privacy-Preserving ML Differential Privacy
PreMeDICaL, Inria, Université de Montpellier, INSERM, France · Technical University of Munich, Germany · Work done while visiting PreMeDICaL, Inria.
An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees
May 19, 2026Hoang Tran, Jorge Ramirez, Jiayi Wang +3Fine-Tuning Privacy-Preserving ML
Computer Science and Mathematics Division, Oak Ridge National Laboratory, Oak Ridge, TN, 37831, USA · Departamento de Matem´aticas, Universidad Nacional de Colombia, Medell´ın, Colombia. · Computational Science and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, 37831, USA +1
SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning
May 19, 2026Mohammad Partohaghighi, Roummel MarciaDeep Learning Optimization Differentially Private Stochastic Gradient Descent
Department of Electrical Engineering and Computer Science University of California, Merced Merced, CA, USA · Department of Applied Mathematics University of California, Merced Merced, CA, USA
Auditing Privacy in Multi-Tenant RAG under Account Collusion
May 19, 2026Florian A. D. BurnatData Leakage Privacy Auditing
University of Bath, Bath, UK.
A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning
May 19, 2026T. Tony Cai, Yicheng LiDifferentially Private Federated Learning Differential Privacy
Department of Statistics and Data Science, The Wharton School, University of Pennsylvania, Philadelphia, PA, USA. · KLATASDS-MOE, School of Statistics, East China Normal University, Shanghai, China.
FedMental: Evaluating Federated Learning for Mental Health Detection from Social Media Data
May 18, 2026Nuredin Ali Abdelkadir, Anjali Ratnam, Zeerak Talat +1Depression Detection Mental Health
University of Minnesota · University of Edinburgh
Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
May 18, 2026Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson +2Differentially Private Stochastic Gradient Descent Differential Privacy
Institute of Science and Technology Austria · University of Helsinki
Jacobian-Guided Anisotropic Noise Reshaping for Enhancing Representation Utility under Local Differential Privacy
May 16, 2026Youngmok Ha, Viktor Schlegel, Yidan Sun +1Privacy-Preserving ML Differential Privacy
Department of Bioengineering, Imperial College London, United Kingdom · Artificial Intelligence Computing Research Laboratory, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea · Imperial Global Singapore, Imperial College London, Singapore +1
The Privacy Price of Tail-Risk Learning: Effective Tail Sample Size in Differentially Private CVaR Optimization
May 15, 2026El Mustapha MansouriStochastic Optimization Differential Privacy
School of Engineering, Institute of Science Tokyo, Yokohama, Kanagawa 226-8501, Japan
Differentially Private Motif-Preserving Multi-modal Hashing
May 14, 2026Zehua Cheng, Wei Dai, Jiahao SunCross-Modal Learning Cross-Modal Retrieval
Department of Computer Science University of Oxford Oxford, United Kingdom · FLock.io London, United Kingdom
Limits of Personalizing Differential Privacy Budgets
May 13, 2026Edwige Cyffers, Juba ZianiDifferential Privacy Privacy-Utility Tradeoff
CNRS, LAMSADE, Dauphine-PSL · Georgia Institute of Technology.
Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
May 12, 2026Puyu Wang, Jan Schuchardt, Nikita Kalinin +4Differentially Private Stochastic Gradient Descent Nonconvex Stochastic Optimization
RPTU Kaiserslautern-Landau, Kaiserslautern, Germany · Machine Learning Research, Morgan Stanley · Institute of Science and Technology, Klosterneuburg, Austria +1
How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation
May 11, 2026Eduardo Tenorio, Karuna Bhaila, Xintao WuSocial Bias in Language Models Language Model Bias Evaluation
University of Arkansas
Differentially Private Sampling from Distributions via Wasserstein Projection
May 11, 2026Shokichi Takakura, Seng Pei Liew, Satoshi HasegawaDifferential Privacy
LY Corporation
Deep Learning under Fractional-Order Differential Privacy
May 11, 2026Mohammad Partohaghighi, Roummel MarciaDifferentially Private Stochastic Gradient Descent Privacy-Preserving ML
MESA Lab, Dept. of EECS University of California, Merced Merced, CA 95343 · Dept. of Applied Mathematics University of California, Merced Merced, CA 95343
Privacy-Preserving Distributed Learning in IoT Systems: A Unified Threat Model and Evaluation Framework
May 10, 2026John Cartmell, Alexander WilliamsInternet of Things Privacy-Preserving ML
Department of Electrical Engineering and Computer Science
INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
May 8, 2026Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +1Differentially Private Stochastic Gradient Descent Differential Privacy
Department of Computer Science, National University of Singapore · Agency for Science, Technology and Research (A*STAR), Singapore
Differentially Private Auditing Under Strategic Response
May 8, 2026Florian A. D. BurnatPrivacy Auditing Algorithmic Auditing
University of Bath
Modulated learning for private and distributed regression with just a single sample per client device
May 8, 2026Praneeth Vepakomma, Amirhossein Reisizadeh, Samuel Horváth +1Differentially Private Federated Learning Differential Privacy
Massachusetts Institute of Technology (MIT) · Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)
Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
May 8, 2026Andy Dong, Ayfer ÖzgürDifferentially Private Stochastic Gradient Descent Differential Privacy
Stanford University
Towards Differentially Private Reinforcement Learning with General Function Approximation
May 7, 2026Yi He, Xingyu ZhouRegret Minimization in RL Reinforcement Learning
Wayne State University, Detroit, USA
Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
May 7, 2026Marten van Dijk, Murat Bilgehan ErtanDifferentially Private Stochastic Gradient Descent Differential Privacy
CWI Amsterdam · ∗Affiliated with Vrije Universiteit Amsterdam.
Quadratic Objective Perturbation: Curvature-Based Differential Privacy
May 7, 2026Daniel Cortild, Coralia CartisPrivacy-Preserving ML Differential Privacy
Mathematical Institute, University of Oxford, Oxford, United Kingdom
Adaptive Selection of LoRA Components in Privacy-Preserving Federated Learning
May 7, 2026Myoungjun Kim, Sangwoo Park, Yoseob Han +1Federated Learning Aggregation Low-Rank Adaptation
Myongji University · King’s College London · Soongsil University

May 26, 2026, cs.LGJ/K move · Enter open · S save

Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run

Mathieu Dagréou, Aurélien Bellet

PreMeDICaL team, Inria · Idesp, Inserm, Univ. de Montpellier

Privacy Auditing Membership Inference Attacks Differential Privacy

Open paper AskPDF arXiv

Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy (DP) parameters. Recent one-run auditing methods address the high cost of standard approaches by relying on a single training run with multiple "canary" points whose inclusion or exclusion must be detected by the auditor. In this work, we study the problem of efficiently crafting canaries for one-run privacy auditing. Motivated by recent theoretical insights suggesting that interference between canaries contributes to weaker leakage estimates compared to multi-run methods, we propose to optimize canaries to be both highly detectable and minimally interfering. Our approach combines a greedy initialization based on influence functions with a bilevel optimization procedure that maximizes distinguishability while promoting diversity in embedding space, enabling the use of computationally efficient bilevel algorithms. Experiments show that our method achieves stronger privacy leakage estimates at a lower computational cost than existing canary crafting approaches.