Privacy-preserving image retrieval based on additive secret sharing in cloud environment

With the development of cloud computing, more and more resource constrained data owners tend to store their images in the cloud and rely on image retrieval services to get back images they want. However, this process raises huge privacy leakage risks. Privacy-preserving image retrieval (PPIR) can prevent privacy leakage during the retrieval process. Using convolutional neural networks for image feature extraction can significantly improve retrieval accuracy and has become a common trend in PPIR, but it also brings a new problem of network model parameter leakage, which is often ignored by most PPIR schemes. Besides, existing PPIR schemes often adopt centralized image retrieval service, which typically require frequent interactions between the cloud server and users during the retrieval process, resulting in excessive computational overhead for resource-limited users. Aiming to solve these problems, a distributed privacy-preserving image retrieval scheme is proposed in this paper. Three collaborative cloud servers utilize three neural network models split and outsourced by the data owner to extract features of the query image and perform subsequent retrieval tasks. A new secure Euclidean distance calculation protocol is designed for cloud servers to measure feature similarity, and secure sort pair protocol, secure sorting protocol, secure search protocol are utilized to achieve secure image retrieval. Additionally, a hierarchical index tree is employed to narrow down the search scope and improve search efficiency. This approach avoids the problem of network model parameter leakage caused by using neural networks to extract image features at the users' side, reduces the computational burden on users, and improves the accuracy and the efficiency of the retrieval process while ensuring retrieval security. Security analysis and experimental results demonstrate the security and retrieval performance of the proposed scheme.