Privacy-Preserving Representation Learning

Follow this topic Ask about this topic

Latest papers

9 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

FedPix: Learning What to Share with Less Leakage in Federated Intelligence
Oct 15, 2026Jingwei Zhao, Tiantong Sun, Yuanyuan Song +6Privacy-Preserving Representation Learning Privacy-Preserving ML
Huazhong University of Science and Technology, Wuhan, China · George Mason University, Fairfax, VA, USA
Privacy-Preserving Deep Joint Source-Channel Coding with In-Loop Concept Erasure
Sep 11, 2026Rami Eid, Maria Slim, Mariette Awad +1Deep Joint Source-Channel Coding Privacy-Preserving ML
Department of Electrical and Computer Engineering, American University of Beirut, Beirut 1107 2020, Lebanon
Chemical and geometric representation fidelity improves drug--target affinity prediction
Sep 2, 2026Yixiao Li, Yining Qian, Yefan Chen +5Privacy-Preserving Representation Learning Protein-Ligand Binding Affinity Prediction
College of Information Science and Engineering, Northeastern University, Shenyang 110819, China · School of Computer and Communication Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, China · School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China +1
TrustCLIP: Learning Private Visual Features via Adversarial Reconstruction
Jul 5, 2026Nikos Athanasiou, Ilya A. Petrov, Angela Yao +7Gradient Inversion Attacks VLM Robustness
Meta, Zürich, Switzerland · Max Planck Institute for Intelligent Systems, Tübingen, Germany · University of Tübingen, Germany +1
Distributed Deep Variational Approach for Privacy-preserving Data Release
May 4, 2026Zahir Alsulaimawi, Huaping LiuInformation Bottleneck Privacy-Preserving ML
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
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
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
CFD-HAR: User-controllable Privacy through Conditional Feature Disentanglement
Mar 12, 2026Alex Gn, Fan Li, S Kuniyilh +1Privacy-Preserving Representation Learning Human Activity Recognition

Oct 15, 2026J/K move · Enter open · S save

FedPix: Learning What to Share with Less Leakage in Federated Intelligence

Jingwei Zhao, Tiantong Sun, Yuanyuan Song, Jinhuan Guo+5

Huazhong University of Science and Technology, Wuhan, China · George Mason University, Fairfax, VA, USA

Privacy-Preserving Representation Learning Privacy-Preserving ML Federated Learning Learned Image Compression

Open paper AskPDF arXiv

Existing federated intelligence paradigms primarily focus on how models are trained or aggregated, while overlooking a more fundamental question: what information should leave the client? Existing methods often share model updates that users cannot easily inspect, or data representations that may reveal sensitive information. Moreover, generating these representations can be computationally expensive for resource-constrained clients. We observe that image classification does not require all the visual details needed to reconstruct the original image. This suggests that clients could share less information while preserving task performance. However, learning what to preserve is challenging when the server cannot access raw client data. To address this challenge, we propose FedPix, which learns to share compact, visually inspectable images instead of model updates or intermediate features. The key idea is to use the shared representations themselves to learn what information should be preserved and what can be discarded. By balancing task utility and reconstruction resistance, FedPix enables the server to improve the representations without accessing raw client data, while keeping client-side computation lightweight. Extensive experiments on BloodMNIST, CIFAR-10, FashionMNIST, and MNIST demonstrate that FedPix achieves strong reconstruction resistance, with reconstruction PSNR as low as 6.87~~dB and synthetic PSNR as low as 6.74~~dB. Meanwhile, FedPix reduces client runtime by up to 96.0% (from 1223~~s to 49~~s on CIFAR-10), while maintaining competitive classification accuracy of 99.18% on MNIST, 89.97% on FashionMNIST, 82.24% on BloodMNIST, and 65.63% on CIFAR-10.