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.

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems
Apr 3, 2026Zhaoting Gong, Ran Ran, Fan Yao +1Efficient Transformer Inference Homomorphic Encryption
North Carolina State University, Raleigh, NC, USA · University of Central Florida, Orlando, FL, USA
Unlocking Multi-Site Clinical Data: A Federated Approach to Privacy-First Child Autism Behavior Analysis
Apr 3, 2026Guangyu Sun, Wenhan Wu, Zhishuai Guo +3Autism Spectrum Disorder Privacy-Preserving ML
Institute of Artificial Intelligence, University of Central Florida · Department of Computer Science, University of North Carolina at Charlotte · Department of Computer Science, Northern Illinois University +2
Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition
Apr 2, 2026Anderson Augusma, Dominique Vaufreydaz, Fédérique LetuéEmotion Recognition Privacy-Preserving ML
UGA, LIG, M-PSI · Univ. Grenoble Alpes, CNRS, Grenoble INP, LIG, 38000 Grenoble, France · Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, 38000 Grenoble, France +2
QoS-Aware Token Scheduling and Private Data Valuation for Multi-Modal Agentic Networks
Apr 2, 2026Yao Du, Jing Liu, Pengfei Xu +4Data Valuation Algorithmic Fairness
The University of British Columbia · LazAI Network · China University of Mining and Technology +2
DISCO-TAB: A Hierarchical Reinforcement Learning Framework for Privacy-Preserving Synthesis of Complex Clinical Data
Apr 1, 2026Arshia Ilaty, Hossein Shirazi, Amir Rahmani +1Synthetic Tabular Data Generation Privacy-Preserving ML
Computational Science Research Center, San Diego State University, San Diego, CA 92182 USA. · School of Nursing and Department of Computer Science, University of California, Irvine, CA 92697 USA. · Fowler College of Business, San Diego State University, San Diego, CA 92182 USA. +1
Differentially Private Manifold Denoising
Apr 1, 2026Jiaqi Wu, Yiqing Sun, Zhigang YaoPrivacy-Preserving ML Differential Privacy
Department of Statistics and Data Science, National University of Singapore
PrivHAR-Bench: A Graduated Privacy Benchmark Dataset for Video-Based Action Recognition
Apr 1, 2026Samar AnsariPrivacy-Utility Tradeoff Human Activity Recognition
School of Computer and Engineering Sciences University of Chester Chester, CH1 4BJ, United Kingdom
Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models
Mar 31, 2026Gabriel Loiseau, Damien Sileo, Damien Riquet +2Privacy-Preserving ML Language Model Distillation
Hornetsecurity, Hem, France · Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 - CRIStAL, F-59000 Lille, France
Unsafe2Safe: Controllable Image Anonymization for Downstream Utility
Mar 30, 2026Mih Dinh, SouYoung JinPrivacy-Preserving ML Diffusion-Based Image Editing
Dartmouth College
Key-Embedded Privacy for Decentralized AI in Biomedical Omics
Mar 30, 2026Rongyu Zhang, Hongyu Dong, Gaole Dai +13Privacy-Preserving ML Federated Learning
School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, 210023, China. · Department of Computing, The Hong Kong Polytechnic University, Hong Kong, 999077, China. · State Key Laboratory of Multimedia Information Processing, Peking University, Beijing, 100871, China. +8
Neural Federated Learning for Livestock Growth Prediction
Mar 30, 2026Shoujin Wang, Mingze Ni, Wei Liu +6Federated Learning Time Series Forecasting
University of Technology Sydney, Sydney, Australia · AgriWebb, Sydney, Australia · Queensland University of Technology, Brisbane, Australia
On the Optimal Number of Grids for Differentially Private Non-Interactive $K$ -Means Clustering
Mar 27, 2026Gokularam Muthukrishnan, Anshoo TandonPrivacy-Preserving ML Differential Privacy
The authors are with the Center of Data for Public Good, Foundation for Science Innovation and Development, Indian Institute of Science, Bengaluru 560012, India
Only Whats Necessary: Pareto Optimal Data Minimization for Privacy Preserving Video Anomaly Detection
Mar 27, 2026Nazia Aslam, Abhisek Ray, Thomas B. Moeslund +1Privacy-Preserving ML Privacy-Utility Tradeoff
Aalborg University, Denmark · Aarhus University, Denmark · Milestone System, Denmark
From Pixels to Privacy: Temporally Consistent Video Anonymization via Token Pruning for Privacy Preserving Action Recognition
Mar 27, 2026Nazia Aslam, Abhisek Ray, Joakim Bruslund Haurum +2Privacy-Preserving ML Visual Token Pruning
Aalborg University, Denmark · Aarhus University, Denmark · Poineer Centre for AI, Denmark +2
Privacy-Accuracy Trade-offs in High-Dimensional LASSO under Perturbation Mechanisms
Mar 27, 2026Ayaka Sakata, Haruka TanzawaApproximate Message Passing Privacy-Preserving ML
Department of Information Science, Ochanomizu University · RIKEN center for AIP
Knowledge-Guided Retrieval-Augmented Generation for Zero-Shot Psychiatric Data: Privacy Preserving Synthetic Data Generation
Mar 26, 2026Adam Jakobsen, Sushant Gautam, Hugo Lewi Hammer +4Synthetic Clinical Data Generation Synthetic Tabular Data Generation
∗SimulaMet, Norway · †Oslo Metropolitan University, Norway · ‡Uppsala University, Sweden
Amplified Patch-Level Differential Privacy for Free via Random Cropping
Mar 25, 2026Kaan Durmaz, Jan Schuchardt, Sebastian Schmidt +1Personalized Differential Privacy Privacy-Preserving ML
Technical University of Munich · Machine Learning Research, Morgan Stanley
Efficient Encrypted Computation in Convolutional Spiking Neural Networks with TFHE
Mar 25, 2026Longfei Guo, Pengbo Li, Ting Gao +3Privacy-Preserving ML Efficient Neural Network Inference
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, China · Center for Mathematical Science, Huazhong University of Science and Technology, Wuhan, China · School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, China +3
A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
Mar 24, 2026Najeeb Jebreel, David Sánchez, Josep Domingo-FerrerMembership Inference Attacks Privacy-Preserving ML
Universitat Rovira i Virgili, Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, ComSCIAM-Center for Computational Science and Applied Mathematics Av. Països Catalans 26, 43007 Tarragona, Catalonia
Privacy-Preserving EHR Data Transformation via Geometric Operators: A Human-AI Co-Design Technical Report
Mar 24, 2026Maolin Wang, Beining Bao, Gan Yuan +9Electronic Health Records Privacy-Preserving ML
Hong Kong Institute of AI for Science (HKAI-Sci), City University of Hong Kong · Department of Biostatistics, City University of Hong Kong · YIDU TECH co. Ltd. +1
Privacy-Preserving Reinforcement Learning from Human Feedback via Decoupled Reward Modeling
Mar 23, 2026Young Hyun Cho, Will Wei SunPrivacy-Preserving ML Privacy-Preserving Language Models
Purdue University
mmFHE: mmWave Sensing with End-to-End Fully Homomorphic Encryption
Mar 23, 2026Tanvir Ahmed, Yixuan Gao, Adnan Armouti +1mmWave Radar Sensing Remote Sensing
Cornell Tech
Knowledge Priors for Identity-Disentangled Open-Set Privacy-Preserving Video FER
Mar 22, 2026Feng Xu, Xun Li, Lars Petersson +3Facial Expression Recognition Privacy-Preserving ML
School of CSE, UNSW Sydney, Australia · CSIRO’s Data61, Australia
Adversarial Attacks on Locally Private Graph Neural Networks
Mar 21, 2026Matta Varun, Ajay Kumar Dhakar, Yuan Hong +1Adversarial Attacks Graph Neural Networks
Indian Institute of Technology Kharagpur, India · University of Connecticut, USA
Meeting in the Middle: A Co-Design Paradigm for FHE and AI Inference
Mar 20, 2026Bernardo Magri, Benjamin Marsh, Paul GebheimHomomorphic Encryption Privacy-Preserving ML
University of Manchester · Sei Labs · University of Portsmouth
Face anonymization preserving facial expressions and photometric realism
Mar 18, 2026Luigi Celona, Simone Bianco, Raimondo SchettiniPrivacy-Preserving ML
Department of Informatics, Systems and Communication, University of Milano-Bicocca, 20126 Milan, Italy
FastPFRec: A Fast Personalized Federated Recommendation with Secure Sharing
Mar 18, 2026Zhenxing Yan, Jidong Yuan, Yongqi Sun +2Recommender Systems Federated Learning
Key Laboratory of Big Data & Artificial Intelligence in Transportation (Beijing Jiaotong University), Ministry of Education, Beijing, 100044, China · School of Computer Science and Technology, Beijing Jiaotong University, Beijing, 100044, China
WebPII: Benchmarking Visual PII Detection for Computer-Use Agents
Mar 18, 2026Nathan ZhaoPII Detection Privacy-Preserving ML
Stanford University
Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
Mar 17, 2026Federico Albanese, Pablo Ronco, Nicolás D'IppolitoPrivacy-Preserving ML Privacy-Preserving Language Models
Veritran, Buenos Aires, Argentina · University of Buenos Aires, Argentina · University of San Andrés, Buenos Aires, Argentina
NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs
Mar 17, 2026Zhaohui WangZero-Knowledge ML Privacy-Preserving ML
USC Viterbi School of Engineering, Los Angeles, CA, USA

Apr 3, 2026J/K move · Enter open · S save

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

Zhaoting Gong, Ran Ran, Fan Yao, Wujie Wen

North Carolina State University, Raleigh, NC, USA · University of Central Florida, Orlando, FL, USA

Efficient Transformer Inference Homomorphic Encryption Privacy-Preserving ML GPU Acceleration Tensor Parallelism

Open paper AskPDF arXiv

Fully Homomorphic Encryption (FHE) enables privacy-preserving Transformer inference, but long-sequence encrypted Transformers quickly exceed single-GPU memory capacity because encoded weights are already large and encrypted activations grow rapidly with sequence length. Multi-GPU execution therefore becomes unavoidable, yet scaling remains challenging because communication is jointly induced by application-level aggregation and encryption-level RNS coupling. Existing approaches either synchronize between devices frequently or replicate encrypted tensors across devices, leading to excessive communication and latency. We present AEGIS, an Application-Encryption Guided Inference System for scalable long-sequence encrypted Transformer inference on multi-GPU platforms. AEGIS derives device placement from ciphertext dependencies jointly induced by Transformer dataflow and CKKS polynomial coupling, co-locating modulus-coherent and token-coherent data so that communication is introduced only when application dependencies require it, while reordering polynomial operators to overlap the remaining collectives with computation. On 2048-token inputs, AEGIS reduces inter-GPU communication by up to 57.9% in feed-forward networks and 81.3% in self-attention versus prior state-of-the-art designs. On four GPUs, it achieves up to 96.62% scaling efficiency, 3.86x end-to-end speedup, and 69.1% per-device memory reduction. These results establish coordinated application-encryption parallelism as a practical foundation for scalable homomorphic Transformer inference.