A Novel Discrete Memristor-Coupled Heterogeneous Dual-Neuron Model and Its Application in Multi-Scenario Image Encryption

2025-05-30

AI Summary

To address the need for real-time, secure transmission of law enforcement images in complex environments, this paper proposes a discrete memristor-coupled heterogeneous dual-neuron network (MHDNN) model—the first discrete heterogeneous neural dynamical model driven by memristors. The work systematically characterizes its initial-value- and parameter-dependent stability, multimodal spiking behaviors, and synchronization mechanisms, enabling the design of a lightweight chaotic image encryption algorithm. Methodologically, it integrates discrete dynamical modeling, memristive circuit simulation, STM32-based embedded deployment, and a multi-level scrambling-diffusion encryption scheme. Two custom embedded hardware platforms are developed, achieving real-time MHDNN execution on STM32 with an encryption throughput of 28.6 MB/s. The scheme demonstrates robust resistance against differential, statistical, and noise attacks. The solution has been successfully deployed in mobile law enforcement terminals for secure image transmission.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Security and Privacy: Applications of cryptography
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Measurement, analysis, and circumvention of Web censorship

Abstract

Simulating brain functions using neural networks is an important area of research. Recently, discrete memristor-coupled neurons have attracted significant attention, as memristors effectively mimic synaptic behavior, which is essential for learning and memory. This highlights the biological relevance of such models. This study introduces a discrete memristive heterogeneous dual-neuron network (MHDNN). The stability of the MHDNN is analyzed with respect to initial conditions and a range of neuronal parameters. Numerical simulations demonstrate complex dynamical behaviors. Various neuronal firing patterns are investigated under different coupling strengths, and synchronization phenomena between neurons are explored. The MHDNN is implemented and validated on the STM32 hardware platform. An image encryption algorithm based on the MHDNN is proposed, along with two hardware platforms tailored for multi-scenario police image encryption. These solutions enable real-time and secure transmission of police data in complex environments, reducing hacking risks and enhancing system security.

Problem

• Develops a discrete memristive dual-neuron model for brain simulation
• Analyzes stability and dynamics of heterogeneous neuron networks
• Proposes image encryption for secure police data transmission

Innovation

• Discrete memristor-coupled heterogeneous dual-neuron model
• STM32 hardware platform implementation
• Multi-scenario police image encryption algorithm