Metrics
9 Record Views
Conference proceeding
Privacy-Preserving Self-Supervised Learning for Secure Image Processing: A BYOL-Based Framework for MNIST and Chest X-ray Data
Proceedings: 2025 IEEE 49th Annual Computers, Software, and Applications Conference COMPSAC 2025, pp.1136-1145
IEEE Annual International Computer Software and Applications Conference
Annual Computers, Software, and Applications Conference (COMPSAC), 49th (Toronto, Ontario, Canada, 07/08/2025–07/11/2025)
08/26/2025
Web of Science ID: WOS:001575960000139
Abstract
The increasing use of high-dimensional imaging in medical AI raises significant privacy and security concerns. This paper presents a Bootstrap Your Own Latent (BYOL)-based self-supervised learning (SSL) framework for secure image processing, ensuring compliance with HIPAA and privacy-preserving machine learning (PPML) techniques. Our method integrates federated learning, homomorphic encryption, and differential privacy to enhance security while reducing dependence on labeled data. Experimental results on the MNIST and NIH Chest X-ray datasets demonstrate a classification accuracy of 97.5% and 99.99% (pre-fine-tuning 40%), with improved clustering performance using K-Means (Silhouette Score: 0.5247). These findings validate BYOL's capability for robust, privacy-preserving image processing while emphasizing the need for fine-tuning to optimize classification performance.
Related links
Details
- Title
- Privacy-Preserving Self-Supervised Learning for Secure Image Processing
- Publication Details
- Proceedings: 2025 IEEE 49th Annual Computers, Software, and Applications Conference COMPSAC 2025, pp.1136-1145
- Resource Type
- Conference proceeding
- Conference
- Annual Computers, Software, and Applications Conference (COMPSAC), 49th (Toronto, Ontario, Canada, 07/08/2025–07/11/2025)
- Publisher
- IEEE; ieeexplore
- Series
- IEEE Annual International Computer Software and Applications Conference
- Number of pages
- 10
- Grant note
- National Science Foundation NSF ML4CS Grants: 2433800, 1946442 NIH Ubitrix Grant: 5R42LM014356-03
This work was supported by the National Science Foundation NSF ML4CS Grants #2433800, #1946442 and the NIH Ubitrix Grant #5R42LM014356-03. The views expressed are those of the authors and do not necessarily reflect those of the NSF or NIH.
- Copyright
- © 2025, IEEE
- Identifiers
- WOS:001575960000139; 99381484295206600
- Academic Unit
- Center for Cybersecurity
- Language
- English