Secure Image Retrieval Based on Deep CNN Features in Cloud Computing
Zhongkui Fan, Yepeng Guan · 2022
In cloud computing era, data owners become increasingly motivated to outsource their images from local sites to the commercial public cloud for great flexibility and economic savings. For the consideration of users' privacy, sensitive images have to be encrypted before outsourcing, which makes effective data utilization a very challenging task. Image CNN features are once considered confidential for image retrieval in cloud computing. However, recent studies have shown that these features contain ambiguous semantic information and can be reconstructed to images. We design a computable encryption scheme based on vector and matrix calculations for the risk of CNN feature-based image retrieval. The scheme uses SIFT and CNN features to pre-build a feature-based index to provide feature-related information about each encrypted image and then chooses the efficient image similarity measure as the pruning tool to carry out the retrieval procedure. Security analysis and performance evaluation show that the scheme is INI-CCA. The experimental results show that the proposed method has achieved excellent results on content-based image retrieval.