JPEG2000 COMPATIBLE NEURAL NETWORK BASED CIPHER

In this paper, an efficient encryption technique is proposed, especially for JPEG2000 compatible images. The technique uses a multi-layer neural network to generate a pseudo-random sequence for transforming wavelet subbands into cipher subbands. The neural network generator takes 64 bit key as a startup seed with additional 64 bit key for initial weights and biases. At each layer, output is calculated by several iterations to increase the complexity of the pseudorandom sequence generation. In order to examine effectiveness of this approach, various tests including correlation, histogram, key space etc. are conducted on test images, and the results demonstrate the robustness of the proposed approach.