Image sharing based on 3D-BCNN and Blockchain Authentication

Abstract In the current trend of cloud storage and data sharing, image trading and consumption are increasingly frequent. Therefore, the protection of sensitive images and identity authentication become urgent. In this paper, an image sharing method based on 3-dimensional Boolean convolution neural network (3D-BCNN) and blockchain is proposed. Unlike traditional symmetric encryption algorithms, this paper introduces an asymmetric key cryptosystem, which allow different users to receive image with authorization without knowing the key of the data owner. The correctness authentication of the acquired image is based on blockchain, which is immutable and reliable. In pre-transmission encryption, 3D convolution matrices are designed by Chaotic Restricted Boltzmann Machine(CRBM), convolution kernel and shuffle rule are generated by novel two-parameters wide-range mapping mixed Coupled Map Lattice (TWM-CML), and each channel performs Boolean XOR convolution operation. The experimental simulation shows that the secret image has better security properties than the state-of-the-art algorithms. Furthermore, the algorithm provides an end-to-end trusted image protection system and authenticate efficiently.