Privacy-Preserving ML

ML: Machine Learning

Ask about this topic

Overview

The field studies how to train, evaluate, and deploy machine-learning systems while reducing disclosure of personal data, model information, or sensitive patterns. Main approaches include differential privacy during optimization, federated learning with secure aggregation, homomorphic encryption and secure multiparty computation, as well as synthetic data, representation obfuscation, and machine unlearning. Methods are tested across clinical, language, vision, and graph tasks, using measures such as prediction quality, reconstruction and membership-inference attacks, communication, and runtime. A central tension is that federated learning or transformed data do not guarantee privacy on their own, while stronger formal protections can reduce utility or add substantial computational and communication costs.

Latest papers

CardsList

433 papers37 papers in the last four weeks, down 3% on the four weeks before. 0.2% of all new papers.

  1. Private Rate-Constrained Optimization with Applications to Fair Learning

    May 28, 2025Mohammad Yaghini, Tudor Cebere, Michael Menart +2Primal-Dual OptimizationGroup Fairness

    University of Toronto · Vector Institute · PreMeDICaL team +3

  2. Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI

    May 28, 2025Santhosh Parampottupadam, Melih Coşğun, Sarthak Pati +7Federated Learning AggregationDifferentially Private Stochastic Gradient Descent

    German Cancer Research Center (DKFZ), Division of Medical Image Computing, Heidelberg, Germany · Department of Computer Engineering, Bilkent University, Universiteler 06800 Çankaya/Ankara, Türkiye · Medical Research Group, MLCommons, San Francisco, CA, USA +2

  3. CO-DEFEND: Continuous Decentralized Federated Learning for Secure DoH-Based Threat Detection

    Apr 2, 2025Diego Cajaraville-Aboy, Marta Moure-Garrido, Carlos Beis-Penedo +5Network Intrusion DetectionEncrypted Network Traffic Analysis

    atlanTTic Research Center – ICLAB – Universidade de Vigo, Vigo, 36310, Spain · Department of Telematic Engineering, Universidad Carlos III de Madrid, Spain

  4. From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

    Mar 15, 2025Yan Jiang, Hao Yu, Xu Cheng +3Privacy-Preserving MLVisible-Infrared Person Re-Identification

    Center for Machine Vision and Signal Analysis, University of Oulu, Oulu FI-90014, Finland · School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

  5. Split-n-Chain: Privacy-Preserving Multi-Node Split Learning with Blockchain-Based Auditability

    Mar 10, 2025Mukesh Sahani, Binanda SenguptaPrivacy-Preserving MLDistributed Training

    Indian Institute of Technology (Indian School of Mines) Dhanbad, India · Indian Institute of Engineering Science and Technology, Shibpur, India

  6. Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation Model

    Feb 8, 2025Zinan Lin, Tadas Baltrusaitis, Wenyu Wang +1Differentially Private Synthetic Data GenerationSynthetic Data Generation

    Microsoft Research Redmond, WA, USA · Microsoft Cambridge, UK · Redmond, WA, USA

  7. Batch effects can impair federated learning in multi-center omics studies

    Dec 8, 2024Yuliya Burankova, Julian Klemm, Jens J. G. Lohmann +5Batch Effect CorrectionSecure Multi-Party Computation

    Institute for Computational Systems Biomedicine, University of Hamburg, 22761 Hamburg, Germany · Chair of Proteomics and Bioanalytics, TUM School of Life Sciences, Technical University of Munich, 85354 Freising, Germany · Department of Mathematics and Computer Science, University of Southern Denmark, 5230 Odense, Denmark +3

  8. DNA: Differentially private Neural Augmentation for contact tracing

    Apr 20, 2024Rob Romijnders, Christos Louizos, Yuki M. Asano +1Privacy-Preserving MLDifferential Privacy

    University of Amsterdam · Qualcomm AI research

  9. PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples

    Mar 10, 2024Zhuo Zhang, Jingyuan Zhang, Jintao Huang +6Privacy Leakage in Language ModelsFew-Shot Learning

    Harbin Institute of Technology, Shenzhen, China · Peng Cheng Lab, Shenzhen, China · Kuaishou, Beijing, China +1

  10. PEARL: Structural Privacy-Utility Control in Human-Centric CPS via Personalized Early-Exit Deep Reinforcement Learning

    Mar 9, 2024Mojtaba Taherisadr, Salma ElmalakiRL ControlCyber-Physical Systems

    University of California, Irvine, USA

  11. Label Differential Privacy via Aggregation

    Oct 16, 2023Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar +3Privacy-Preserving MLDifferential Privacy

    Google Research India.

  12. A Differentially Private Weighted Empirical Risk Minimization Procedure and its Application to Outcome Weighted Learning

    Jul 24, 2023Spencer Giddens, Yiwang Zhou, Kevin R. Krull +3Privacy-Preserving MLDifferential Privacy

    University of Notre Dame, Notre Dame, IN 46556, USA · St. Jude Children’s Research Hospital, Memphis, TN 38138, USA · University of Michigan, Ann Arbor, MI 48109, USA

  13. Privacy-Preserving Logistic Regression Training with A Faster Gradient Variant

    Jan 26, 2022John ChiangLogistic RegressionGradient Descent