Secure Medical Image Processing and Analysis Using SQL-Based Hybrid Encoding and LWE-Inspired Encryption

DOI

10.2991/978-94-6239-789-7_12How to use a DOI?

Keywords

Medical Image Encryption; Learning with Errors; SQL-based Processing; Homomorphic Encryption; Medical Data Security; PSNR; SSIM

Abstract

This paper presents a novel SQL-based secure processing framework for medical images that combines hybrid encoding with a Learning with Errors (LWE)-inspired encryption scheme. Traditional encryption methods require decryption before any computation, which introduces security risks. The proposed system enables limited homomorphic operations (specifically addition) directly on encrypted data stored in the database, thereby preserving confidentiality while allowing processing.

The framework first applies byte-level and Unicode-level encoding to the image data, followed by LWE-inspired encryption. All operations are implemented entirely within Microsoft SQL Server using stored procedures. Experimental results on medical images show high randomness in the encrypted data and excellent reconstruction quality of the decrypted images, achieving accuracy up to 99% along with satisfactory PSNR and SSIM values.

Copyright

© 2026 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  - Vikrant Sharma
AU  - Shikha Verma
PY  - 2026
DA  - 2026/10/08
TI  - Secure Medical Image Processing and Analysis Using SQL-Based Hybrid Encoding and LWE-Inspired Encryption
BT  - Proceedings of theInternational Conference on Innovation and Practices in Artificial Intelligence (ICIPAI 2026)
PB  - Atlantis Press
SP  - 162
EP  - 171
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-789-7_12
DO  - 10.2991/978-94-6239-789-7_12
ID  - Sharma2026
ER  -