Finite-Time Projective Synchronization of Memristor-Based BAM Neural Networks and Applications in Image Encryption

Abstract

Inspired by security applications in the image transmission, this paper focuses on the usage of chaotic properties of memristor-based bidirectional associate memory neural networks (MBAMNNs) for image encryption against illegal attack. A class of memristor-based bidirectional associate memory neural networks with delays and stochastic perturbations is formulated and analyzed. Based on drive-response concept, Ito’s differential formula and inequality technique, some sufficient criteria are obtained to guarantee the finite-time projective synchronization. In order to realize the image encryption, we propose a chaotic color image encryption algorithm based on MBAMNNs. Illustrative examples are provided to verify the developed finite-time projective synchronization results. And we also show the great chaotic properties of the models proposed in this paper. Analysis of the encryption effect demonstrated the security of the proposed image encryption algorithm, and the potential applications of our models in secure image transmission are analyzed.