Secure Multi-Party Computation for Machine Learning: A Survey
Machine learning is a powerful technology for extracting information from data of diverse nature and origin. As its deployment increasingly depends on data from multiple entities, ensuring privacy for these contributors becomes paramount for the integrity and fairness of machine learning endeavors....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10498135/ |
| _version_ | 1827276300611485696 |
|---|---|
| author | Ian Zhou Farzad Tofigh Massimo Piccardi Mehran Abolhasan Daniel Franklin Justin Lipman |
| author_facet | Ian Zhou Farzad Tofigh Massimo Piccardi Mehran Abolhasan Daniel Franklin Justin Lipman |
| author_sort | Ian Zhou |
| collection | DOAJ |
| description | Machine learning is a powerful technology for extracting information from data of diverse nature and origin. As its deployment increasingly depends on data from multiple entities, ensuring privacy for these contributors becomes paramount for the integrity and fairness of machine learning endeavors. This review looks into the recent advancements in secure multi-party computation (SMPC) for machine learning, a pivotal technology championing data privacy. We evaluate these applications from various aspects, including security models, requirements, system types, and service models, aligning with the IEEE’s recommended practices for SMPC. Broadly, SMPC systems are divided into two categories: homomorphic-based systems, which facilitate computations on encrypted data, ensuring data remains confidential, and secret sharing-based systems, which disseminate data across parties in fragmented shares. Our literature analysis highlights certain gaps, such as security requisites, streamlined information exchange, incentive structures, data authenticity, and operational efficiency. Recognizing these challenges lead to envisioning a holistic SMPC protocol tailored for machine learning applications. |
| first_indexed | 2024-04-24T06:41:56Z |
| format | Article |
| id | doaj.art-2bd5400750a24acfb506fe8967e393a4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-24T06:41:56Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2bd5400750a24acfb506fe8967e393a42024-04-22T23:00:23ZengIEEEIEEE Access2169-35362024-01-0112538815389910.1109/ACCESS.2024.338899210498135Secure Multi-Party Computation for Machine Learning: A SurveyIan Zhou0https://orcid.org/0000-0002-7154-4561Farzad Tofigh1https://orcid.org/0000-0003-1802-488XMassimo Piccardi2https://orcid.org/0000-0001-9250-6604Mehran Abolhasan3https://orcid.org/0000-0002-4282-6666Daniel Franklin4https://orcid.org/0000-0002-9563-5943Justin Lipman5https://orcid.org/0000-0003-2877-1168School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaSchool of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaSchool of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaSchool of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaSchool of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaSchool of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, AustraliaMachine learning is a powerful technology for extracting information from data of diverse nature and origin. As its deployment increasingly depends on data from multiple entities, ensuring privacy for these contributors becomes paramount for the integrity and fairness of machine learning endeavors. This review looks into the recent advancements in secure multi-party computation (SMPC) for machine learning, a pivotal technology championing data privacy. We evaluate these applications from various aspects, including security models, requirements, system types, and service models, aligning with the IEEE’s recommended practices for SMPC. Broadly, SMPC systems are divided into two categories: homomorphic-based systems, which facilitate computations on encrypted data, ensuring data remains confidential, and secret sharing-based systems, which disseminate data across parties in fragmented shares. Our literature analysis highlights certain gaps, such as security requisites, streamlined information exchange, incentive structures, data authenticity, and operational efficiency. Recognizing these challenges lead to envisioning a holistic SMPC protocol tailored for machine learning applications.https://ieeexplore.ieee.org/document/10498135/Multi-party computationmachine learningfederated learningdata privacycryptographyprotocols |
| spellingShingle | Ian Zhou Farzad Tofigh Massimo Piccardi Mehran Abolhasan Daniel Franklin Justin Lipman Secure Multi-Party Computation for Machine Learning: A Survey IEEE Access Multi-party computation machine learning federated learning data privacy cryptography protocols |
| title | Secure Multi-Party Computation for Machine Learning: A Survey |
| title_full | Secure Multi-Party Computation for Machine Learning: A Survey |
| title_fullStr | Secure Multi-Party Computation for Machine Learning: A Survey |
| title_full_unstemmed | Secure Multi-Party Computation for Machine Learning: A Survey |
| title_short | Secure Multi-Party Computation for Machine Learning: A Survey |
| title_sort | secure multi party computation for machine learning a survey |
| topic | Multi-party computation machine learning federated learning data privacy cryptography protocols |
| url | https://ieeexplore.ieee.org/document/10498135/ |
| work_keys_str_mv | AT ianzhou securemultipartycomputationformachinelearningasurvey AT farzadtofigh securemultipartycomputationformachinelearningasurvey AT massimopiccardi securemultipartycomputationformachinelearningasurvey AT mehranabolhasan securemultipartycomputationformachinelearningasurvey AT danielfranklin securemultipartycomputationformachinelearningasurvey AT justinlipman securemultipartycomputationformachinelearningasurvey |