Privacy Preserving Deep Learning with Learnable Image Encryption on Medical Images

DOI

10.2991/978-94-6463-858-5_216How to use a DOI?

Keywords

Secure Medical Imaging; Secure Tumor Classification; Confidential AI diagnostics; Data Protection

Abstract

Deep learning has made significant progress in medical imaging by improving diagnostic accuracy. However, processing sensitive patient data on cloud-based platforms introduces major privacy risks. This study introduces a privacy-centric approach to analysing medical images, utilizing learnable encryption methods to process encrypted data directly via deep neural networks lacking decryption. By leveraging sophisticated convolutional neural network designs with dense connectivity structures and enhanced feature extraction, the system ensures high tumor classification accuracy while maintaining end-to-end data security throughout both training and inference. Evaluated on a brain MRI dataset, the framework delivers strong diagnostic performance along with stringent privacy safeguards. For practical deployment, the system is integrated into a Flask- based web application, providing a user-friendly interface for tumor detection while maintaining patient confidentiality. This work bridges the gap between AI-driven diagnostic accuracy and regulatory-compliant data security, offering a scalable and secure solution for real-world healthcare applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jarupula Rajeshwar
AU  - Somarajupalli Thejaswi
AU  - Salendra Manoj Kumar
AU  - Sunkapaka John
PY  - 2025
DA  - 2025/11/04
TI  - Privacy Preserving Deep Learning with Learnable Image Encryption on Medical Images
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 2604
EP  - 2618
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_216
DO  - 10.2991/978-94-6463-858-5_216
ID  - Rajeshwar2025
ER  -