mlsanityData to 14 Oct 2026

PPFL-RDSN: Privacy-Preserving Federated Learning-based Residual Dense Spatial Networks for Encrypted Lossy Image Reconstruction

arXiv 2507.00230 ↗First posted 30 Jun 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Reconstructing high-quality images from low-resolution inputs using Residual Dense Spatial Networks (RDSNs) is crucial yet challenging. It is even more challenging in centralized training where multiple collaborating parties are involved, as it poses significant privacy risks, including data leakage and inference attacks, as well as high computational and communication costs. We propose a novel Privacy-Preserving Federated Learning-based RDSN (PPFL-RDSN) framework specifically tailored for encrypted lossy image reconstruction. PPFL-RDSN integrates Federated Learning (FL), local differential privacy, and robust model watermarking techniques to ensure that data remains secure on local clients/devices, safeguards privacy-sensitive information, and maintains model authenticity without revealing underlying data. Empirical evaluations show that PPFL-RDSN achieves comparable performance to the state-of-the-art centralized methods while reducing computational burdens, and effectively mitigates security and privacy vulnerabilities, making it a practical solution for secure and privacy-preserving collaborative computer vision applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 46 of its 78 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

46 of 78 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  8. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  9. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  10. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  11. 2018How To Backdoor Federated Learningcited by 765
  12. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
34 more
  1. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  2. 2021Federated Learning on Non-IID Data: A Surveycited by 346
  3. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  4. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  5. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 211
  6. 2020Threats to Federated Learning: A Surveycited by 178
  7. 2017Asynchronous Decentralized Parallel Stochastic Gradient Descentcited by 159
  8. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 156
  9. 2017Revisiting Distributed Synchronous SGDcited by 142
  10. 2020Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challengescited by 139
  11. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  12. 2021Federated Learning: Opportunities and Challengescited by 84
  13. 2020Gradient Centralization: A New Optimization Technique for Deep Neural Networkscited by 82
  14. 2021Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learningcited by 78
  15. 2020A Systematic Review on Model Watermarking for Neural Networkscited by 52
  16. 2019Local Differential Privacy for Deep Learningcited by 46
  17. 2018Deep Convolutional AutoEncoder-based Lossy Image Compressioncited by 42
  18. 2021FedIPR: Ownership Verification for Federated Deep Neural Network Modelscited by 36
  19. 2021Specificity-Preserving Federated Learning for MR Image Reconstructioncited by 35
  20. 2017Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learningcited by 34
  21. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 34
  22. 2022Federated Learning of Generative Image Priors for MRI Reconstructioncited by 33
  23. 2020Privacy Preserving Face Recognition Utilizing Differential Privacycited by 30
  24. 2022Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domaincited by 28
  25. 2021Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancementcited by 17
  26. 2024Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocationcited by 14
  27. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  28. 2020Timely Communication in Federated Learningcited by 9
  29. 2022Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix Itcited by 8
  30. 2022Precision-based attacks and interval refining: how to break, then fix, differential privacy on finite computerscited by 8
  31. 2021Federated Learning Versus Classical Machine Learning: A Convergence Comparisoncited by 7
  32. 2024DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-trainingcited by 7
  33. 2021Secure Random Sampling in Differential Privacycited by 5
  34. 2018Image Reconstruction Using Deep Learningcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Federated Learning Nodes Can Reconstruct Peers' Image Data
  2. 2025Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy
  3. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learning
  4. 2025CSVAR: Enhancing Visual Privacy in Federated Learning via Adaptive Shuffling Against Overfitting ↗
  5. 2025Enhanced Privacy Leakage from Noise-Perturbed Gradients via Gradient-Guided Conditional Diffusion Models
  6. 2026Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images
  7. 2025Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models
  8. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments