Privacy-Preserving ML

ML: Machine Learning

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

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

Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference
Feb 23, 2026Hong Wang, Xuwei Fan, Zhipeng Cheng +4Constrained MARL Efficient Neural Network Inference
School of Future Science and Engineering, Soochow University, Suzhou 215006, China · College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China · School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China +2
Evaluating the Impact of Data Anonymization on Image Retrieval
Feb 23, 2026Marvin Chen, Manuel Eberhardinger, Johannes MaucherImage Retrieval Privacy-Preserving ML
Institute of Applied AI, Stuttgart Media University, Nobelstr. 10, 70569 Stuttgart, Germany
HybridFL: A Federated Learning Approach for Financial Crime Detection
Feb 22, 2026Afsana Khan, Marijn ten Thij, Guangzhi Tang +1Anti-Money Laundering Federated Learning
Department of Advanced Computing Sciences, Maastricht University, Netherlands · Department of Cognitive Science and Artificial Intelligence, Tilburg University, Netherlands
SLDP: Semi-Local Differential Privacy for Density-Adaptive Analytics
Feb 21, 2026Alexey Kroshnin, Alexandra SuvorikovaDifferential Privacy Privacy-Preserving ML
Weierstrass Institute for Applied Analysis and Stochastic
PrivacyBench: Privacy Isn't Free in Hybrid Privacy-Preserving Vision Systems
Feb 21, 2026Nnaemeka Obiefuna, Samuel Oyeneye, Similoluwa Odunaiya +2Privacy-Preserving ML Differential Privacy
1ML Collective · 2Friedrich-Alexander-Universität Erlangen-Nürnberg · 3Carnegie Mellon University
DP-RFT: Learning to Generate Synthetic Text via Differentially Private Reinforcement Fine-Tuning
Feb 20, 2026Fangyuan Xu, Sihao Chen, Zinan Lin +13Differentially Private Synthetic Data Generation Synthetic Data Generation for Language Models
New York University · Microsoft · University of Southern California
JAX-Privacy: A library for differentially private machine learning
Feb 19, 2026Ryan McKenna, Galen Andrew, Borja Balle +6Privacy-Preserving ML Differential Privacy
Guarding the Middle: Protecting Intermediate Representations in Federated Split Learning
Feb 19, 2026Obaidullah Zaland, Sajib Mistry, Monowar BhuyanTraining Data Reconstruction Attacks Privacy-Preserving ML
Department of Computing Science, Umeå Unviersity, Umeå, SE-90187, Sweden · Curtin University, Bentley WA 6102, Australia
Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
Feb 19, 2026Wyatt Benno, Alberto Centelles, Antoine Douchet +1Zero-Knowledge ML Privacy-Preserving ML
ICME Labs
MeGU: Machine-Guided Unlearning with Target Feature Disentanglement
Feb 19, 2026Haoyu Wang, Zhuo Huang, Xiaolong Wang +3Machine Unlearning Privacy-Preserving ML
School of Automation, Beijing Institute of Technology · Sydney AI Centre, The University of Sydney · Department of Computer Science, Hong Kong Baptist University
Protecting the Undeleted in Machine Unlearning
Feb 18, 2026Aloni Cohen, Refael Kohen, Kobbi Nissim +1Training Data Reconstruction Attacks Machine Unlearning
University of Chicago · Tel Aviv University · Dept. of Computer Science, Georgetown University
Utility-Preserving De-Identification for Math Tutoring: Investigating Numeric Ambiguity in the MathEd-PII Benchmark Dataset
Feb 18, 2026Zhuqian Zhou, Kirk Vanacore, Bakhtawar Ahtisham +7PII Detection Privacy-Preserving ML
Cornell University · Fresh Cognate · UPchieve +1
Hybrid Federated and Split Learning for Privacy Preserving Clinical Prediction and Treatment Optimization
Feb 17, 2026Farzana Akter, Rakib Hossain, Deb Kanna Roy Toushi +3Uplift Modeling Privacy-Preserving ML
Dept. of Information Technology, Washington University of Science and Technology, Alexandria, VA, USA · Cognitive Links LLC, Maryland, USA
LRD-MPC: Efficient MPC Inference through Low-rank Decomposition
Feb 16, 2026Tingting Tang, Yongqin Wang, Murali AnnavaramPrivacy-Preserving ML Efficient Neural Network Inference
University of Southern California, Los Angeles, California, USA
ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregation
Feb 9, 2026Dario Fenoglio, Pasquale Polverino, Akash Dhasade +3Federated Learning Federated Learning Aggregation
Universit`a della Svizzera italiana Lugano, Switzerland · Carnegie Mellon University Pittsburgh, PA, United States
Taipan: A Query-free Transfer-based Multiple Sensitive Attribute Inference Attack Solely from Auxiliary Graphs
Feb 6, 2026Ying Song, Balaji PalanisamyPrivacy-Preserving ML
University of Pittsburgh Pittsburgh, PA, USA
FaceLinkGen: A Re-evaluation of Identity Leakage in Privacy-Preserving Face Recognition and Face Anonymization Systems Using Simple Distillation
Feb 2, 2026Wenqi Guo, Qingyun Qian, Mohamed Shehata +1Model Inversion Attacks Privacy-Preserving ML
Department of Computer Science, Mathematics, Physics and Statistics University of British Columbia, Kelowna, BC, Canada
On the Inherent Privacy Amplification of Missing Data
Feb 2, 2026Simon Roburin, Rafa{ë}l Pinot, Erwan ScornetPrivacy-Preserving ML Differential Privacy
LPSM · Sorbonne Université, Université Paris Cité, CNRS Laboratoire de Probabilités, Statistique et Modélisation (LPSM) F-75005 Paris, France
Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective
Jan 30, 2026Georgi Ganev, Emiliano De CristofaroPrivacy Auditing Synthetic Tabular Data Generation
UCL · SAS · UC Riverside
FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation
Dec 21, 2025Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana +4Federated Learning Aggregation Video Content Moderation
School of Computing, Macquarie University, Sydney, Australia · School of Computer Science, The University of Sydney, Sydney, Australia · School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia
Federated Computation of ROC and PR Curves
Oct 6, 2025Xuefeng Xu, Graham CormodePrivacy-Preserving ML Secure Aggregation
University of Warwick
Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning
Sep 26, 2025Li Xia, Jing Yu, Zheng Liu +3Gradient Inversion Attacks Adversarial Attacks
Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, 100081, China
Membership Inference Attacks on Recommender System: A Survey
Sep 14, 2025Jiajie He, Xintong Chen, Xinyang Fang +4Membership Inference Attacks Privacy-Preserving ML
University of Maryland, Baltimore County, USA · Mcmaster University, Canada · University of Southern California, USA +1
Privacy-Preserving Generation of Clinical Narratives from Medical Terminologies
Sep 13, 2025Yuping Wu, Viktor Schlegel, Warren Del-Pinto +11Medical Report Generation Healthcare
Univeristy of Manchester · Imperial College London, Imperial Global Singapore · Khoo Teck Puat Hospital, Singapore +2
Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
Sep 1, 2025Sayan Biswas, Philippe Chartier, Akash Dhasade +7Privacy-Preserving ML Homomorphic Encryption
EPFL · Inria · IRMAR +3
Algorithmic Shortlisting in Participatory Budgeting
Aug 7, 2025Juan Ignacio Zambrano, Clément Contet, Jairo Gudiño-Rosero +3Learning to Rank Privacy-Preserving ML
IRIT · Université Toulouse Capitole · Université de Toulouse +3
High-Dimensional Differentially Private Quantile Regression: Distributed Estimation and Statistical Inference
Aug 7, 2025Ziliang Shen, Caixing Wang, Shaoli Wang +1Quantile Regression Privacy-Preserving ML
School of Statistics and Data Science, Shanghai University of Finance and Economics · School of Statistics and Data Science, Southeast University · School of Statistics and Data Science, Shanghai University of International Business and Economics
Efficient Unlearning with Privacy Guarantees
Jul 7, 2025Josep Domingo-Ferrer, Najeeb Jebreel, David SánchezPrivacy-Preserving ML Machine Unlearning
1CYBERCAT (Center for Cybersecurity Research of2026 Catalonia), ComSCIAM-Center for Computational Science and Applied Mathematics, Department of Computer EngineeringJun and Mathematics, Universitat Rovira i Virgili, Av. Pa¨ısos26 Catalans 26, E-43007 Tarragona, Catalonia
Federated Learning for MRI-based BrainAGE: a multicenter study on post-stroke functional outcome prediction
Jun 18, 2025Vincent Roca, Marc Tommasi, Paul Andrey +8Brain Age Prediction Clinical Outcome Prediction
Univ. Lille, CNRS, Inserm, CHU Lille, Institut Pasteur de Lille, US 41 - UAR 2014 - PLBS, F-59000 Lille, France · Univ. Lille, Inria, F-59000 Lille, France · Univ. Montpellier, Inria, F-34090 Montpellier, France +3
Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
Jun 4, 2025Hang Liu, Anna Scaglione, Sean PeisertPrivacy-Preserving ML Gaussian Mixture Models
State Key Laboratory of Internet of Things for Smart City and the Department of Electrical and Computer Engineering, University of Macau, Macao S.A.R. · Department of Electrical and Computer Engineering, Cornell Tech, Cornell University, New York, NY, 10044 USA. · Computing Sciences Research, Lawrence Berkeley National Laboratory, Berkeley, CA 94720 USA.

Feb 23, 2026J/K move · Enter open · S save

Safe Multi-Agent Deep Reinforcement Learning for Privacy-Aware Edge-Device Collaborative DNN Inference

Hong Wang, Xuwei Fan, Zhipeng Cheng, Yachao Yuan+3

School of Future Science and Engineering, Soochow University, Suzhou 215006, China · College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China · School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China+2

Constrained MARL Efficient Neural Network Inference Multi-Agent Reinforcement Learning Privacy-Preserving ML

Open paper AskPDF arXiv

As Deep Neural Network (DNN) inference becomes increasingly prevalent on edge and mobile platforms, critical challenges emerge in privacy protection, resource constraints, and dynamic model deployment. This paper proposes a privacy-aware collaborative inference framework, in which adaptive model partitioning is performed across edge devices and servers. To jointly optimize inference delay, energy consumption, and privacy cost under dynamic service demands and resource constraints, we formulate the joint problem as a Constrained Markov Decision Process (CMDP) that integrates model deployment, user-server association, model partitioning, and resource allocation. We propose a Hierarchical Constrained Multi-Agent Proximal Policy Optimization with Lagrangian relaxation (HC-MAPPO-L) algorithm, a safe reinforcement learning-based framework that enhances Multi-Agent Proximal Policy Optimization (MAPPO) with adaptive Lagrangian dual updates to enforce long-term delay constraints. To ensure tractability while maintaining coordination, we decompose the CMDP into three hierarchically structured policy layers: an auto-regressive based model deployment policy, a Lagrangian-enhanced user association and model partitioning policy, and an attention-based resource allocation policy. Extensive experimental results demonstrate that HC-MAPPO-L consistently satisfies stringent delay constraints while achieving a superior balance among energy consumption and privacy cost, outperforming representative baseline algorithms across varying problem scales and resource configurations.