Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Peilin He, James Joshi

TL;DR

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.

Abstract

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.

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

TL;DR

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.

Abstract

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.

Paper Structure

This paper contains 29 sections, 22 equations, 7 figures, 3 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Background and Related Work
  3. Deep learning-based RDSN
  4. Federated Learning
  5. The Proposed PPFL-RDSN Framework
  6. Threat Modeling and Mitigation
  7. Local Differential Privacy (LDP)
  8. Step 1: Data-independent orthogonal transform.
  9. Step 2: Deterministic low/high‑frequency partition.
  10. Step 3: Clipping and sensitivity.
  11. Step 4: Gaussian mechanism on $C_H$.
  12. Algorithm 1: LDP-ClientUpdate.
  13. Model Watermarking
  14. Watermark key and carrier subset.
  15. Training‑time embedding via regularisation.
  16. ...and 14 more sections

Figures (7)

  • Figure 1: An Overview of the PPFL-RDSN Framework
  • Figure 2: Effect of privacy budgets on the overall PSNR and SSIM for different $\epsilon$ values.
  • Figure 3: Effect of privacy budgets on the overall PSNR and SSIM for different $\epsilon$ values.
  • Figure 4: Effect of the number of epochs on the overall PSNR and SSIM for different $\epsilon$ values.
  • Figure 5: Performance comparison for PSNR between State-of-the-Art and our FL-RDSN
  • ...and 2 more figures