Design and realization of a new chaotic neural encryption/decryption network

Abstract

A new chaotic neural network and its VLSI architecture for digital signal encryption and decryption are proposed in the paper. According to a binary sequence generated from a chaotic system, the biases and weights of neurons are set. The chaotic neural network can be used to encrypt digital signals. The network's features are as follows: (1) high security; (2) no distortion; and (3) suitable for system integration. The MATLAB simulation results are also included for demonstration. In order to implement the system, its VLSI architecture with low hardware complexity and high computing speed is also designed. Its FPGA realization result indicates that the proposed design works correctly and its encryption speed achieves 40 Mbps. It indicates that the integration of the proposed system and MPEG2 for TV distribution, communication, and storage is practicable.