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.

Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption
Apr 25, 2026Alexandre Marques, Beatriz Sá, Rui Botelho +1Homomorphic Encryption Privacy-Preserving ML
ISEP, School of Engineering, Polytechnic of Porto, Porto, Portugal · GECAD, Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Porto, Portugal
Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization
Apr 24, 2026Jeonggon Kim, Heejoon Moon, Je Hyeong HongCamera Pose Estimation Privacy-Preserving ML
Dept. Electronic Engineering, Hanyang University · Dept. Artificial Intelligence, Hanyang University
Differentially Private Model Merging
Apr 22, 2026Qichuan Yin, Manzil Zaheer, Tian LiPrivacy-Preserving ML Differential Privacy
The University of Chicago · Google DeepMind
Onyx: Cost-Efficient Disk-Oblivious ANN Search
Apr 22, 2026Deevashwer Rathee, Jean-Luc Watson, Zirui Neil Zhao +2Privacy-Preserving ML Approximate Nearest Neighbor Search
UC Berkeley, NVIDIA · NVIDIA · UT Austin, NVIDIA +1
Federated Learning over Blockchain-Enabled Cloud Infrastructure
Apr 21, 2026Saloni Garg, Amit Sagtani, Kamal Kant HiranPrivacy-Preserving ML Blockchain-Based Federated Learning
Adobe Research San Jose, USA · San Francisco State University San Francisco, USA · Sir Padampat Singhania University Udaipur, India
Sherpa.ai Privacy-Preserving Multi-Party Entity Alignment without Intersection Disclosure for Noisy Identifiers
Apr 21, 2026Daniel M. Jimenez-Gutierrez, Dario Pighin, Enrique Zuazua +4Privacy-Preserving ML Federated Learning
Federated Rule Ensemble Method in Medical Data
Apr 20, 2026Ke Wan, Kensuke Tanioka, Toshio ShimokawaInterpretable ML Privacy-Preserving ML
Department of Medical Data Science Wakayama Medical University · Department of Biomedical Sciences and Informatics Doshisha University · Department of Biostatistics Wakayama Medical University
Channel-Level Semantic Perturbations: Unlearnable Examples for Diverse Training Paradigms
Apr 18, 2026Bo Wang, Jia Ni, Mengnan Zhao +2Adversarial Examples Privacy-Preserving ML
School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China · School of Computer Science and Technology, Anhui University, Hefei 230601, China · School of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
Towards Deep Encrypted Training: Low-Latency, Memory-Efficient, and High-Throughput Inference for Privacy-Preserving Neural Networks
Apr 18, 2026Nges Brian Njungle, Eric Jahns, Michel A. KinsyEfficient Neural Network Inference Memory-Efficient Inference
STAM Center, Ira A. Fulton Schools of Engineering · Arizona State University, Tempe, AZ 85281, USA
Privacy-Preserving LLMs Routing
Apr 17, 2026Xidong Wu, Yukuan Zhang, Yuqiong Ji +3Secure Multi-Party Computation Privacy-Preserving ML
Department of Electrical and Computer Engineering, University of Pittsburgh · Department of Computer Science, University of Central Florida · Department of Computer and Information Science, University of Pennsylvania +2
SecureRouter: Encrypted Routing for Efficient Secure Inference
Apr 16, 2026Yukuan Zhang, Mengxin Zheng, Qian LouEfficient Transformer Inference Secure Multi-Party Computation
University of Central Florida · Orlando, Florida, USA
Privacy-Preserving Semantic Segmentation without Key Management
Apr 16, 2026Mare Hirose, Shoko Imaizumi, Hitoshi KiyaPrivacy-Preserving ML Semantic Segmentation
Chiba University · Tokyo Metropolitan University
VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymization
Apr 14, 2026Miit Daga, Swarna Priya RamuPrivacy Auditing Verifiable Outsourced Computation
School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, Tamil Nadu, India
CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
Apr 14, 2026Qi Li, Cheng-Long Wang, Yinzhi Cao +1Privacy-Preserving ML Membership Inference Attacks
King Abdullah University of Science and Technology · Provable Responsible AI and Data Analytics Lab · National University of Singapore +1
Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition
Apr 13, 2026Ünsal Öztürk, Vedrana Krivokuća Hahn, Sushil Bhattacharjee +1Representation Disentanglement Face Recognition
Idiap Research Institute, Martigny, Switzerland · UNIL, Lausanne, Switzerland
Mitigating Privacy Risk via Forget Set-Free Unlearning
Apr 12, 2026Aviraj Newatia, Michael Cooper, Viet Nguyen +1Machine Unlearning Privacy-Preserving ML
University of Toronto, Vector Institute, Toronto, ON, Canada
FEDBUD: Joint Incentive and Privacy Optimization for Resource-Constrained Federated Learning
Apr 12, 2026Tao Liu, Xuehe WangIncentive Mechanisms for Federated Learning Federated Learning
School of Artificial Intelligence, Sun Yat-sen University, Zhuhai 519082, China
Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
Apr 10, 2026Joanna KomorniczakSynthetic Tabular Data Generation Generative Modeling
Department of Systems and Computer Networks, Wrocław University of Science and Technology
Using Synthetic Data for Machine Learning-based Childhood Vaccination Prediction in Narok, Kenya
Apr 10, 2026Jimmy Bach, Yang Li, Yaqi Liu +5Privacy-Preserving ML
William & Mary Williamsburg, VA, United States · Ignite Global Health Research Lab, William & Mary Global Research Institute Williamsburg, VA, USA · William & Mary Department Williamsburg, VA, USA +4
Retrieval Augmented Classification for Confidential Documents
Apr 9, 2026Yeseul E. Chang, Rahul Kailasa, Simon Shim +2Retrieval-Augmented Classification Text Classification
Department of Security Convergence, Chung-Ang University, Seoul, South Korea · Department of Applied Data Science, San Jose State University, San Jose, CA, United States · Department of Industrial Security, Chung-Ang University, Seoul, South Korea
TADP-RME: A Trust-Adaptive Differential Privacy Framework for Enhancing Reliability of Data-Driven Systems
Apr 9, 2026Labani Halder, Payel Sadhukhan, Sarbani PalitPrivacy-Preserving ML Differential Privacy
Indian Statistical Institute Kolkata 203 B.T. Road, Kolkata-700108, India · Army Institute of Management Plot No III/B-11, Action Area III, New Town, Kolkata-700160, India
CSA-Graphs: A Privacy-Preserving Structural Dataset for Child Sexual Abuse Research
Apr 8, 2026Carlos Caetano, Camila Laranjeira, Clara Ernesto +5Scene Graphs Image Classification
Universidade Estadual de Campinas (UNICAMP), Brazil · Instituto Federal de Educação, Ciência e Tecnologia de Minas Gerais (IFMG), Brazil · Universidade de São Paulo (USP), Brazil +3
A Utility-preserving De-identification Pipeline for Cross-hospital Radiology Data Sharing
Apr 8, 2026Chenhao Liu, Zelin Wen, Yan Tong +7Privacy-Preserving ML Healthcare
Shandong University · Hong Kong University of Science and Technology · Australian National University +3
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
Apr 8, 2026Jeongho Yoon, Chanhee Park, Yongchan Chun +2Privacy-Preserving Language Models Privacy-Preserving ML
Department of Computer Science and Engineering, Korea University · Samsung Mobile eXperience Business
Variational Feature Compression for Model-Specific Representations
Apr 8, 2026Zinan Guo, Zihan Wang, Chuan Yan +3Privacy-Preserving Representation Learning Privacy-Preserving ML
The University of Queensland, Brisbane, Australia · University of Wollongong, Wollongong, Australia · City University of Hong Kong, Hong Kong SAR, China
From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal
Apr 7, 2026Daniel George, Charles Yeh, Daniel Lee +1Privacy-Preserving ML Visual Representation Learning
Persona Identities, USA
Protecting and Preserving Protest Dynamics for Responsible Analysis
Apr 6, 2026Cohen Archbold, Usman Hassan, Nazmus Sakib +2Privacy-Preserving ML Social Media Analysis
University of Kentucky, USA
Feature-Aware Anisotropic Local Differential Privacy for Utility-Preserving Graph Representation Learning in Metal Additive Manufacturing
Apr 6, 2026MD Shafikul Islam, Mahathir Mohammad Bappy, Saifur Rahman Tushar +1Privacy-Preserving ML Differential Privacy
Mechanical and Industrial Engineering Louisiana State University Baton Rouge, LA 70803 · Department of Computer Science Missouri University of Science and Technology Missouri S&T, Rolla, MO 65409
DP-OPD: Differentially Private On-Policy Distillation for Language Models
Apr 6, 2026Fatemeh Khadem, Sajad Mousavi, Yi Fang +1Privacy-Preserving Language Models Privacy-Preserving ML
Santa Clara University, Santa Clara, California, USA · Independent Researcher
Stable and Privacy-Preserving Synthetic Educational Data with Empirical Marginals: A Copula-Based Approach
Apr 5, 2026Gabriel Diaz Ramos, Lorenzo Luzi, Debshila Basu Mallick +1Differentially Private Synthetic Data Generation Synthetic Data Generation
Rice University · OpenStax · Rice University, OpenStax

Apr 25, 2026J/K move · Enter open · S save

Training Machine Learning Models on Encrypted Data: A Privacy-Preserving Framework using Homomorphic Encryption

Alexandre Marques, Beatriz Sá, Rui Botelho, Pedro Pinto

ISEP, School of Engineering, Polytechnic of Porto, Porto, Portugal · GECAD, Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development, Porto, Portugal

Homomorphic Encryption Privacy-Preserving ML

Open paper AskPDF arXiv

The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest or in transit but fail to secure it during processing, exposing it to unauthorized access. Homomorphic encryption emerges as a transformative solution, enabling computations on encrypted data without decryption, thus preserving confidentiality throughout the ML pipeline. This paper addresses the challenge of training ML models on encrypted data while maintaining accuracy and efficiency by proposing a proof-of-concept for a privacy-preserving framework that leverages Cheon-Kim-Kim-Song (CKKS) for approximate real-number arithmetic. Also, it demonstrates the feasibility of training K-Nearest Neighbors (KNN) and linear regression models on encrypted data, and evaluates encrypted inference for a basic Multilayer Perceptron (MLP) architecture. Experimental results show that models trained under Homomorphic encryption achieve performance metrics comparable to plaintext-trained models, validating the approach. However, challenges such as computational overhead, noise management, and limited support for non-polynomial operations persist. This work lays the groundwork for broader adoption of privacy-preserving ML in real-world applications, balancing security with computational feasibility.