Abstract
With the tremendous growth of smart mobile devices, the Content-Based Image Retrieval (CBIR) becomes popular and has great market potentials. Secure image retrieval has attracted considerable interests recently due to users' security concerns. However, it still suffers from the challenges of relieving mobile devices of excessive computation burdens, such as data encryption, feature extraction, and image similarity scoring. In this paper, we propose and implement an IND-CPA secure CBIR framework that performs image retrieval on the cloud without the user's constant interaction. A pre-trained deep CNN model, i.e., VGG-16, is used to extract the deep features of an image. The information about the neural network is strictly concealed by utilizing the lattice-based homomorphic scheme. We implement a real number computation mechanism and a divide-and-conquer CNN evaluation protocol to enable our framework to securely and efficiently evaluate the deep CNN with a large number of inputs. We further propose a secure image similarity scoring protocol, which enables the cloud servers to compare two images without knowing any information about their deep features. The comprehensive experimental results show that our framework is efficient and accurate.
Highlights
It might be a cost-effective way to provide efficient and intelligent Content-Based Image Retrieval (CBIR) services that smart mobile users outsource their images onto cloud servers
Evaluation Metrics: We evaluated the performance of the feature extraction, index construction, and image retrieval, respectively
The communication cost refers to the size of the intermediate data in bytes exchanged between the two servers
Summary
It might be a cost-effective way to provide efficient and intelligent Content-Based Image Retrieval (CBIR) services that smart mobile users outsource their images onto cloud servers. Homomorphic encryption techniques such as Lattice-based schemes [2] can potentially handle such issue, but are not adoptable due to their large computational complexity Another approach is Secure Multi-party Computation (SMC) that supports secure image similarity calculation. We propose and implement a CBIR framework that shifts excessive computations onto the cloud servers, such as IND-CPA secure image re-encryption, deep feature extraction, and image similarity scoring. In this way, a mobile user only needs to encrypt his/her image with a lightweight encryption algorithm and upload the encryption onto the cloud.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
