Subdata image encryption scheme based on compressive sensing and vector quantization

An advanced image encryption scheme should equip the capability against malicious attacks, reduce the losses under attacks, and improve the compression rate tremendously due to the unsafe network environment and the limited bandwidth resources. Recently, compressive sensing (CS) has been introduced into image encryption schemes because of the merit of low sampling rate. However, these schemes still cannot address the above requirements well. In order to improve compression rate while providing higher security level, a novel subdata image cryptosystem is proposed by introducing vector quantization (VQ) into CS-based encryption scheme. The plaintext image is first divided into VQ index blocks and the error compensations that are sparse enough to be compressed by CS. Then, the index information and CS measurements are further scrambled and diffused by chaotic sequences to achieve enhanced security. It can be ensured that the primary index information is informative and occupies smaller proportion of cipher image such that it cannot be easily tampered if only a part of the image is attacked. In contrast, the secondary error information is a good supplement to the former and occupies larger proportion. Simulation results verify that our proposed scheme has overwhelming compression rate and security effect to resist malicious attacks when compared with the state-of-art schemes. In addition, even if the important information is damaged, the destroyed pixels can be located and the plaintext image can be reconstructed with VQ neighbor indexes.