PReDIHERO – Privacy-Preserving Remote Deep Learning Inference based on Homomorphic Encryption and Reversible Obfuscation for Enhanced Client-side Overhead in Pervasive Health Monitoring

Simple item page
dc.contributor.authorBoulemtafes, Amine
dc.contributor.authorDerhab, Abdelouahid
dc.contributor.authorAit Ali Braham, Nassim
dc.contributor.authorChallal, Yacine
dc.date.accessioned2024-02-12T12:36:46Z
dc.date.available2024-02-12T12:36:46Z
dc.date.issued2021
dc.description.abstractHomomorphic Encryption is one of the most promising techniques to deal with privacy concerns, which is raised by remote deep learning paradigm, and maintain high classification accuracy. However, homomorphic encryption-based solutions are characterized by high overhead in terms of both computation and communication, which limits their adoption in pervasive health monitoring applications with constrained client-side devices. In this paper, we propose PReDIHERO, an improved privacy-preserving solution for remote deep learning inferences based on homomorphic encryption. The proposed solution applies a reversible obfuscation technique that successfully protects sensitive information, and enhances the client-side overhead compared to the conventional homomorphic encryption approach. The solution tackles three main heavyweight client-side tasks, namely, encryption and transmission of private data, refreshing encrypted data, and outsourcing computation of activation functions. The efficiency of the client-side is evaluated on a healthcare dataset and compared to a conventional homomorphic encryption approach. The evaluation results show that PReDIHERO requires increasingly less time and storage in comparison to conventional solutions when inferences are requested. At two hundreds inferences, the improvement ratio could reach more than 30 times in terms of computation overhead, and more than 8 times in terms of communication overhead. The same behavior is observed in sequential data and batch inferences, as we record an improvement ratio of more than 100 times in terms of computation overhead, and more than 20 times in terms of communication overhead.
dc.identifier.doi10.1109/AICCSA53542.2021.9686893
dc.identifier.isbn978-1-6654-0970-4
dc.identifier.issn2161-5322
dc.identifier.urihttps://dl.cerist.dz/handle/CERIST/1014
dc.publisherIEEE
dc.relation.ispartofseriesIEEE/ACS 18th International Conference on Computer Systems and Applications (AICCSA); 30 November 2021 - 03 December 2021
dc.relation.pages8p.
dc.relation.placeTangier, Morocco
dc.structureRecherche, Filtrage et Traitement Automatique de l'Information
dc.subjectDeep Learning
dc.subjectNeural Network
dc.subjectHomomorphic Encryption
dc.subjectRandom mask
dc.subjectPrivacy
dc.subjectSensitive data
dc.subjectConstrained
dc.subjectInference
dc.titlePReDIHERO – Privacy-Preserving Remote Deep Learning Inference based on Homomorphic Encryption and Reversible Obfuscation for Enhanced Client-side Overhead in Pervasive Health Monitoring
dc.typeConference paper
Files
Collections
International Conference Papers