Reversible cellular automata image encryption for similarity search

Abstract

With the development of cloud computing, people prefer to outsource images to cloud service for saving storage and convenient retrieval. For privacy-preserving purposes, sensitive images, such as medical and personal images, need to be encrypted before outsourcing, which causes the content-based image retrieval technology on plaintext domain unusable. In order to achieve similarity search on encrypted domain, this paper proposes reversible cellular automata image encryption for similarity search. We firstly define the similarity search on encrypted images, and analyze its feasibility when implementing pixel-based deterministic encryption. According to this, we introduce a deterministic encryption based on reversible cellular automata (DERCA). Then we put forward a two-level-granularity image encryption which supports extracting color histogram from encrypted image for similarity search, based on DERCA. The pixels in an image are encrypted in pixel-granularity or pixel-set-granularity to solve utility-security dilemma. And block-based permutation method is used to improve the image security and retrieval accuracy. Experiments on Corel-1000 demonstrate that the proposed method not only offers high image security, but also yields superior retrieval accuracy on encrypted images compared with other image encryption algorithms for similarity search.