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.

Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification
Mar 16, 2026Emil Hardarson, Luka Biedebach, Ómar Bessi Ómarsson +3Large Language Model-Guided NAS Multivariate Time Series Classification
Reykjavik University, Reykjavik, Iceland · University of Southampton, Southampton, United Kingdom
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
Mar 16, 2026Jeremy J SamuelsonPrivacy-Preserving Representation Learning Privacy-Preserving ML
EVP, Artificial Intelligence & Innovation Integrated Quantum Technologies
Towards Privacy-Preserving Machine Translation at the Inference Stage: A New Task and Benchmark
Mar 16, 2026Wei Shao, Lemao Liu, Yinqiao Li +3Privacy-Preserving ML Machine Translation
City University of Hong Kong · City University of Hong Kong Shenzhen Research Institute · Tencent AI Lab, Shenzhen
Bodhi VLM: Privacy-Alignment Modeling for Hierarchical Visual Representations in Vision Backbones and VLM Encoders via Bottom-Up and Top-Down Feature Search
Mar 14, 2026Bo Ma, Wei Qi Yan, Jinsong WuPrivacy-Preserving Representation Learning Privacy-Preserving ML
Auckland University of Technology, Auckland 1024 NZ · Resideo Technologies, Inc., Austin, TX 78759, USA · Guilin University of Electronic Technology, Gui Lin, China +1
Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
Mar 13, 2026Zakia Zaman, Praveen Gauravaram, Mahbub Hassan +2Privacy-Preserving ML Internet of Things
School of CSE, University of NSW, AU · TCS Research & Innovation, Tata Consultancy Services (Australia & New Zealand), Australia
Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights
Mar 13, 2026Xingli Fang, Jung-Eun KimPrivacy-Preserving ML Privacy-Utility Tradeoff
Department of Computer Science, North Carolina State University, Raleigh, NC 27695, USA
CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement
Mar 12, 2026Alex Gn, Fan Li, S Kuniyilh +1Privacy-Preserving Representation Learning Human Activity Recognition
SNPgen: Phenotype-Supervised Genotype Representation and Synthetic Data Generation via Latent Diffusion
Mar 11, 2026Andrea Lampis, Michela Carlotta Massi, Nicola Pirastu +3Synthetic Data Generation Genomics
DEIB, Politecnico di Milano, Milan 20133, Italy · Health Data Science Centre, Human Technopole, Milan 20157, Italy · Genomics Research Centre, Human Technopole, Milan 20157, Italy +2
Differentially Private Multimodal In-Context Learning
Mar 5, 2026Ivoline C. Ngong, Zarreen Reza, Joseph P. NearPrivacy Protection in VLMs Multimodal ICL
University of Vermont, Burlington, VT, USA · Independent Researcher
Privacy-Aware Camera 2.0 Technical Report
Mar 5, 2026Huan Song, Shuyu Tian, Ting Long +5Video Surveillance Privacy-Preserving ML
Institute of Artificial Intelligence (TeleAI), China Telecom
A Late-Fusion Multimodal AI Framework for Privacy-Preserving Deduplication in National Healthcare Data Environments
Mar 4, 2026Mohammed Omer Shakeel AhmedEntity Resolution Privacy-Preserving ML
University of Texas at Arlington Dallas, USA
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
Mar 4, 2026Madhura Edirisooriya, Dasuni Kawya, Ishan Kumarasinghe +5Medical Image Synthesis Synthetic Data Augmentation
University of Peradeniya, Sri Lanka · University of Maryland, College Park, USA · Tulane University School of Medicine, USA; Simula Research Laboratory, Norway +1
Nearest-Neighbor Density Estimation for Dependency Suppression
Mar 4, 2026Kathleen Anderson, Thomas MartinetzPrivacy-Preserving ML Unsupervised Representation Learning
Institute for Neuro- and Bioinformatics, University of Lübeck, Germany
Why Do Unlearnable Examples Work: A Novel Perspective of Mutual Information
Mar 4, 2026Yifan Zhu, Yibo Miao, Yinpeng Dong +1Unlearnable Examples Privacy-Preserving ML
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences · University of Chinese Academy of Sciences · College of AI, Tsinghua University +1
LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing
Mar 4, 2026Yuanming Cao, Chengqi Li, Wenbo HePrivacy-Preserving ML Differential Privacy
McMaster University, Hamilton, Ontario, Canada
Machine Pareidolia: Protecting Facial Image with Emotional Editing
Mar 4, 2026Binh M. Le, Simon S. WooPrivacy-Preserving ML Image Editing
Sungkyunkwan University, Suwon, South Korea
Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality
Mar 3, 2026Yenan Wang, Carla Fabiana Chiasserini, Elad Michael SchillerPrivacy-Preserving ML Federated Learning
Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden
StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting
Mar 3, 2026Guoqing Ma, Xun Lin, Hui Ma +6Image Forgery Detection Deepfake Detection
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. · School of Future Technology, University of Chinese Academy of Sciences, Beijing 100049, China. · Beihang University, Beijing 100191, China. +2
Differential privacy representation geometry for medical image analysis
Mar 1, 2026Soroosh Tayebi Arasteh, Marziyeh Mohammadi, Sven Nebelung +1Neural Representation Geometry Healthcare
Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany · INDA Institute, RWTH Aachen University, Aachen, Germany
Turning Black Box into White Box: Dataset Distillation Leaks
Mar 1, 2026Huajie Chen, Tianqing Zhu, Yuchen Zhong +7Training Data Reconstruction Attacks Dataset Distillation
City University of Macau · CISPA Helmholtz Center for Information Security · University of Technology Sydney +1
Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
Feb 28, 2026Dariush Wahdany, Matthew Jagielski, Adam Dziedzic +1Privacy-Preserving ML Training Data Curation
CISPA Helmholtz Center for Information Security · Anthropic
MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
Feb 27, 2026Tiantong Wang, Xinyu Yan, Tiantong Wu +3Machine Unlearning LLM Unlearning
College of Computing and Data Science, Nanyang Technological University · Alibaba-NTU Global e-Sustainability CorpLab (ANGEL) · Tongyi Lab, Alibaba Group
Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease
Feb 26, 2026Ines N. Duarte, Praphulla M. S. Bhawsar, Lee K. Mason +4Privacy-Preserving Language Models Privacy-Preserving ML
Division of Cancer Epidemiology and Genetics, National Cancer Institute, National Institutes of Health, Rockville, MD, United States · INESC-ID, R. Alves Redol 9, Lisbon 1000-029, Portugal · Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais, Lisbon 1049-001, Portugal
MAPLE: Metadata Augmented Private Language Evolution
Feb 26, 2026Eli Chien, Yuzheng Hu, Ryan McKenna +3Privacy-Preserving Language Models Differentially Private Synthetic Data Generation
National Taiwan University · University of Illinois Urbana-Champaign · Google Research +1
DP-aware AdaLN-Zero: Taming Conditioning-Induced Heavy-Tailed Gradients in Differentially Private Diffusion
Feb 26, 2026Tao Huang, Jiayang Meng, Xu Yang +2Conditional Diffusion Models Privacy-Preserving ML
School of Computer Science and Big Data, Minjiang University, Fuzhou, Fujian, China. · School of Information, Renmin University of China, Beijing, China.
Differentially Private Truncation of Unbounded Data via Public Second Moments
Feb 25, 2026Zilong Cao, Xuan Bi, Hai ZhangPrivacy-Preserving ML Differential Privacy
School of Mathematics, Northwest University · Department of Information and Decision Sciences, Minnesota Carlson, University of Minnesota
Private and Robust Contribution Evaluation in Federated Learning
Feb 25, 2026Delio Jaramillo Velez, Gergely Biczok, Alexandre Graell i Amat +2Federated Learning Privacy-Preserving ML
University of La Laguna Tenerife, Spain · HUN-REN Hungarian Research Network Budapest, Hungary · Chalmers University Gotheburg, Sweden +2
Bikelution: Federated Gradient-Boosting for Scalable Shared Micro-Mobility Demand Forecasting
Feb 24, 2026Antonios Tziorvas, Andreas Tritsarolis, Yannis TheodoridisSpatiotemporal Forecasting Federated Learning
Department of Informatics, University of Piraeus, Piraeus, Greece
TT-SEAL: TTD-Aware Selective Encryption for Adversarially-Robust and Low-Latency Edge AI
Feb 24, 2026Kyeongpil Min, Sangmin Jeon, Jae-Jin Lee +1Privacy-Preserving ML Edge ML
†Department of Intelligent Semiconductor Engineering, Chung-Ang University, Seoul, Korea
RobPI: Robust Private Inference against Malicious Client
Feb 23, 2026Jiaqi Xue, Mengxin Zheng, Qian LouPrivacy-Preserving ML
University of Central Florida

Mar 16, 2026J/K move · Enter open · S save

Data-Local Autonomous LLM-Guided Neural Architecture Search for Multiclass Multimodal Time-Series Classification

Emil Hardarson, Luka Biedebach, Ómar Bessi Ómarsson, Teitur Hrólfsson+2

Reykjavik University, Reykjavik, Iceland · University of Southampton, Southampton, United Kingdom

Large Language Model-Guided NAS Multivariate Time Series Classification Multimodal Classification Privacy-Preserving ML

Open paper AskPDF arXiv

Applying machine learning to sensitive time-series data is often bottlenecked by the iteration loop: Performance depends strongly on preprocessing and architecture, yet training often has to run on-premise under strict data-local constraints. This is a common problem in healthcare and other privacy-constrained domains (e.g., a hospital developing deep learning models on patient EEG). This bottleneck is particularly challenging in multimodal fusion, where sensor modalities must be individually preprocessed and then combined. LLM-guided neural architecture search (NAS) can automate this exploration, but most existing workflows assume cloud execution or access to data-derived artifacts that cannot be exposed. We present a novel data-local, LLM-guided search framework that handles candidate pipelines remotely while executing all training and evaluation locally under a fixed protocol. The controller observes only trial-level summaries, such as pipeline descriptors, metrics, learning-curve statistics, and failure logs, without ever accessing raw samples or intermediate feature representations. Our framework targets multiclass, multimodal learning via one-vs-rest binary experts per class and modality, a lightweight fusion MLP, and joint search over expert architectures and modality-specific preprocessing. We evaluate our method on two regimes: UEA30 (public multivariate time-series classification dataset) and SleepEDFx sleep staging (heterogeneous clinical modalities such as EEG, EOG, and EMG). The results show that the modular baseline model is strong, and the LLM-guided NAS further improves it. Notably, our method finds models that perform within published ranges across most benchmark datasets. Across both settings, our method reduces manual intervention by enabling unattended architecture search while keeping sensitive data on-premise.