Khoa Nguyen, Mindaugas Budzys, Eugene Frimpong, Tanveer Khan, Antonis Michalas
{"title":"A Pervasive, Efficient and Private Future: Realizing Privacy-Preserving Machine Learning Through Hybrid Homomorphic Encryption","authors":"Khoa Nguyen, Mindaugas Budzys, Eugene Frimpong, Tanveer Khan, Antonis Michalas","doi":"arxiv-2409.06422","DOIUrl":null,"url":null,"abstract":"Machine Learning (ML) has become one of the most impactful fields of data\nscience in recent years. However, a significant concern with ML is its privacy\nrisks due to rising attacks against ML models. Privacy-Preserving Machine\nLearning (PPML) methods have been proposed to mitigate the privacy and security\nrisks of ML models. A popular approach to achieving PPML uses Homomorphic\nEncryption (HE). However, the highly publicized inefficiencies of HE make it\nunsuitable for highly scalable scenarios with resource-constrained devices.\nHence, Hybrid Homomorphic Encryption (HHE) -- a modern encryption scheme that\ncombines symmetric cryptography with HE -- has recently been introduced to\novercome these challenges. HHE potentially provides a foundation to build new\nefficient and privacy-preserving services that transfer expensive HE operations\nto the cloud. This work introduces HHE to the ML field by proposing\nresource-friendly PPML protocols for edge devices. More precisely, we utilize\nHHE as the primary building block of our PPML protocols. We assess the\nperformance of our protocols by first extensively evaluating each party's\ncommunication and computational cost on a dummy dataset and show the efficiency\nof our protocols by comparing them with similar protocols implemented using\nplain BFV. Subsequently, we demonstrate the real-world applicability of our\nconstruction by building an actual PPML application that uses HHE as its\nfoundation to classify heart disease based on sensitive ECG data.","PeriodicalId":501332,"journal":{"name":"arXiv - CS - Cryptography and Security","volume":"130 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Cryptography and Security","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.06422","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Machine Learning (ML) has become one of the most impactful fields of data
science in recent years. However, a significant concern with ML is its privacy
risks due to rising attacks against ML models. Privacy-Preserving Machine
Learning (PPML) methods have been proposed to mitigate the privacy and security
risks of ML models. A popular approach to achieving PPML uses Homomorphic
Encryption (HE). However, the highly publicized inefficiencies of HE make it
unsuitable for highly scalable scenarios with resource-constrained devices.
Hence, Hybrid Homomorphic Encryption (HHE) -- a modern encryption scheme that
combines symmetric cryptography with HE -- has recently been introduced to
overcome these challenges. HHE potentially provides a foundation to build new
efficient and privacy-preserving services that transfer expensive HE operations
to the cloud. This work introduces HHE to the ML field by proposing
resource-friendly PPML protocols for edge devices. More precisely, we utilize
HHE as the primary building block of our PPML protocols. We assess the
performance of our protocols by first extensively evaluating each party's
communication and computational cost on a dummy dataset and show the efficiency
of our protocols by comparing them with similar protocols implemented using
plain BFV. Subsequently, we demonstrate the real-world applicability of our
construction by building an actual PPML application that uses HHE as its
foundation to classify heart disease based on sensitive ECG data.