K-NN Classification under Homomorphic Encryption: Application on a Labeled Eigen Faces Dataset

Document Type


Publication Date


Subject: LCSH

Machine learning, Computer algorithms, Public key cryptography, Computer security, Data encryption (Computer science)


Computer Engineering | Computer Sciences | Electrical and Computer Engineering


The wide deployment of public cloud computing infrastructures has become an appealing solution for the advantages of flexibility and cost saving, but the risk of being exposed to privacy and security issues refrains a lot of customers from risking their sensitive data to the cloud. The data owners do not want to move to the cloud unless the data confidentiality and the privacy of their queries are guaranteed. How can we structure information sharing in the cloud between different parties and fully realize the benefits of cloud computing, and at the same time sensitive attributes/values are kept confidential except for the parties to whom they belong? In this context, we contribute a privacy preserving scheme for face recognition and classification in which a party willing to classify a face instance against a protected face database at the cloud would have this capability without revealing the instance to the cloud or revealing the database to the party.



Publisher Citation

M. Nassar, N. Wehbe and B. A. Bouna, "K-NN Classification under Homomorphic Encryption: Application on a Labeled Eigen Faces Dataset," 2016 IEEE Intl Conference on Computational Science and Engineering (CSE) and IEEE Intl Conference on Embedded and Ubiquitous Computing (EUC) and 15th Intl Symposium on Distributed Computing and Applications for Business Engineering (DCABES), 2016, pp. 546-552, doi: 10.1109/CSE-EUC-DCABES.2016.239.

Check your library