TDADL-IE: A Deep Learning-Driven Cryptographic Architecture for Medical Image Security

TL;DR

The paper tackles secure encryption of medical images for telemedicine and cloud storage by proposing TDADL-IE, a system that fuses a hybrid chaotic sequence generator with a joint nonlinear three-dimensional diffusion mechanism. A 1D-SQCM map refined by BLSTM produces robust chaotic sequences, which are permuted via an ISA and diffused across color channels by TDA. The approach yields a very large key space, strong resistance to differential and statistical attacks, low pixel correlations in ciphertext, and competitive encryption speed. These findings indicate TDADL-IE offers practical, scalable protection for sensitive medical imagery in distributed environments.

Abstract

The rise of digital medical imaging, like MRI and CT, demands strong encryption to protect patient data in telemedicine and cloud storage. Chaotic systems are popular for image encryption due to their sensitivity and unique characteristics, but existing methods often lack sufficient security. This paper presents the Three-dimensional Diffusion Algorithm and Deep Learning Image Encryption system (TDADL-IE), built on three key elements. First, we propose an enhanced chaotic generator using an LSTM network with a 1D-Sine Quadratic Chaotic Map (1D-SQCM) for better pseudorandom sequence generation. Next, a new three-dimensional diffusion algorithm (TDA) is applied to encrypt permuted images. TDADL-IE is versatile for images of any size. Experiments confirm its effectiveness against various security threats. The code is available at \href{https://github.com/QuincyQAQ/TDADL-IE}{https://github.com/QuincyQAQ/TDADL-IE}.

Figures (6)

• Figure 1: The process of the encryption algorithm.
• Figure 2: LSTM training model diagram. a Training diagram of x
• Figure 3: The Illustration of Three-dimensional Diffusion Algorithm (TDA)
• Figure 4: The Lyapunov exponent of 1D-SQCM, 1-DFCS, Sine and 1D-Chebyshev map.
• Figure 5: BLSTM training loss