SecureDL: A privacy preserving deep learning model for image recognition over cloud

Abstract

The key benefits of cloud services such as low cost, access flexibility, and mobility have attracted worldwide users to utilize deep learning algorithms for computer vision. These cloud servers are maintained by third parties, where users are always concerned about sharing their confidential data with them. In this paper, we addressed these concerns for by developing SecureDL, a privacy-preserving image recognition model for encrypted data over cloud. The proposed block-based image encryption scheme is well designed to protect image’s visual information. The scheme constitutes an order-preserving permutation ordered binary number system and pseudo-random matrices. The proposed method is proved to be secure in a probabilistic viewpoint, and using various cryptographic attacks. Experiments are conducted over several image recognition datasets, and the trade-off analytics between the achieved recognition accuracy and data encryption is well described. SecureDL overcomes the storage and computational overheads that occur with fully-homomorphic and multi-party computation based secure recognition schemes.