A Survey of Differential Privacy Techniques for Federated Learning
The problem of data privacy protection in the information age deserves people’s attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos. Differential privacy(DP) technology is applied in federated lea...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818489/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536197454725120 |
|---|---|
| author | Wang Xin Li Jiaqian Ding Xueshuang Zhang Haoji Sun Lianshan |
| author_facet | Wang Xin Li Jiaqian Ding Xueshuang Zhang Haoji Sun Lianshan |
| author_sort | Wang Xin |
| collection | DOAJ |
| description | The problem of data privacy protection in the information age deserves people’s attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos. Differential privacy(DP) technology is applied in federated learning(FL). By adding noise to raw data and model parameters, it can further enhance the degree of data privacy protection. Over the years, differential privacy technology based on federated learning framework has been developed, which is divided into central differential privacy federated learning(CDPFL) and local differential privacy federated learning(LDPFL). Although differential privacy may reduce the accuracy and convergence of federated learning models while protecting data privacy, researchers have proposed a variety of optimization methods to balance privacy protection and model performance. This paper comprehensively expounds the research status of differential privacy techniques based on the federated learning framework, first providing detailed introductions to federated learning and differential privacy technologies, and then summarizing the development status of two types of federated learning differential privacy(DPFL) techniques respectively; for CDPFL, the paper divides the discussion into first proposal of CDP and typical application examples, the impact of Gaussian mechanisms on model accuracy, optimization based on asynchronous differential privacy, and insights from other scholars; for LDPFL, the paper divides the discussion into first proposal of LDP and typical application examples, processing multidimensional data and improving model accuracy, existing methods and optimization for reducing communication costs, balancing privacy protection and data usability, LDPFL based on the Shuffle model, and insights from other scholars; following this, the paper addresses and summarizes the unique challenges introduced by incorporating differential privacy into federated learning and proposes solutions; finally, based on a summary of existing optimization techniques, the paper outlines future directions and specifically discusses three research ideas for enhancing the optimization effects of federated differential privacy: advanced optimization strategies combining Bayesian methods and the Alternating Direction Method of Multipliers (ADMM), integrating lattice homomorphic encryption techniques from cryptography to achieve more efficient differential privacy protection in federated learning, and exploring the application of zero-knowledge proof techniques in federated learning for privacy protection. |
| format | Article |
| id | doaj-art-a73034265551465fa025b9d28b46ecf7 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a73034265551465fa025b9d28b46ecf72025-01-15T00:03:00ZengIEEEIEEE Access2169-35362025-01-01136539655510.1109/ACCESS.2024.352390910818489A Survey of Differential Privacy Techniques for Federated LearningWang Xin0https://orcid.org/0000-0003-1904-7821Li Jiaqian1https://orcid.org/0009-0001-7774-947XDing Xueshuang2https://orcid.org/0009-0004-5580-6295Zhang Haoji3https://orcid.org/0009-0007-7783-2402Sun Lianshan4https://orcid.org/0000-0002-5738-7862College of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, ChinaCollege of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, ChinaCollege of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, ChinaCollege of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, ChinaCollege of Electronic Information and Artificial Intelligence, Shaanxi University of Science and Technology, Xi’an, ChinaThe problem of data privacy protection in the information age deserves people’s attention. As a distributed machine learning technology, federated learning can effectively solve the problem of privacy security and data silos. Differential privacy(DP) technology is applied in federated learning(FL). By adding noise to raw data and model parameters, it can further enhance the degree of data privacy protection. Over the years, differential privacy technology based on federated learning framework has been developed, which is divided into central differential privacy federated learning(CDPFL) and local differential privacy federated learning(LDPFL). Although differential privacy may reduce the accuracy and convergence of federated learning models while protecting data privacy, researchers have proposed a variety of optimization methods to balance privacy protection and model performance. This paper comprehensively expounds the research status of differential privacy techniques based on the federated learning framework, first providing detailed introductions to federated learning and differential privacy technologies, and then summarizing the development status of two types of federated learning differential privacy(DPFL) techniques respectively; for CDPFL, the paper divides the discussion into first proposal of CDP and typical application examples, the impact of Gaussian mechanisms on model accuracy, optimization based on asynchronous differential privacy, and insights from other scholars; for LDPFL, the paper divides the discussion into first proposal of LDP and typical application examples, processing multidimensional data and improving model accuracy, existing methods and optimization for reducing communication costs, balancing privacy protection and data usability, LDPFL based on the Shuffle model, and insights from other scholars; following this, the paper addresses and summarizes the unique challenges introduced by incorporating differential privacy into federated learning and proposes solutions; finally, based on a summary of existing optimization techniques, the paper outlines future directions and specifically discusses three research ideas for enhancing the optimization effects of federated differential privacy: advanced optimization strategies combining Bayesian methods and the Alternating Direction Method of Multipliers (ADMM), integrating lattice homomorphic encryption techniques from cryptography to achieve more efficient differential privacy protection in federated learning, and exploring the application of zero-knowledge proof techniques in federated learning for privacy protection.https://ieeexplore.ieee.org/document/10818489/Differential privacyfederated learningprivacy protectionlattice-based homomorphic encryptionzero-knowledge proofs |
| spellingShingle | Wang Xin Li Jiaqian Ding Xueshuang Zhang Haoji Sun Lianshan A Survey of Differential Privacy Techniques for Federated Learning IEEE Access Differential privacy federated learning privacy protection lattice-based homomorphic encryption zero-knowledge proofs |
| title | A Survey of Differential Privacy Techniques for Federated Learning |
| title_full | A Survey of Differential Privacy Techniques for Federated Learning |
| title_fullStr | A Survey of Differential Privacy Techniques for Federated Learning |
| title_full_unstemmed | A Survey of Differential Privacy Techniques for Federated Learning |
| title_short | A Survey of Differential Privacy Techniques for Federated Learning |
| title_sort | survey of differential privacy techniques for federated learning |
| topic | Differential privacy federated learning privacy protection lattice-based homomorphic encryption zero-knowledge proofs |
| url | https://ieeexplore.ieee.org/document/10818489/ |
| work_keys_str_mv | AT wangxin asurveyofdifferentialprivacytechniquesforfederatedlearning AT lijiaqian asurveyofdifferentialprivacytechniquesforfederatedlearning AT dingxueshuang asurveyofdifferentialprivacytechniquesforfederatedlearning AT zhanghaoji asurveyofdifferentialprivacytechniquesforfederatedlearning AT sunlianshan asurveyofdifferentialprivacytechniquesforfederatedlearning AT wangxin surveyofdifferentialprivacytechniquesforfederatedlearning AT lijiaqian surveyofdifferentialprivacytechniquesforfederatedlearning AT dingxueshuang surveyofdifferentialprivacytechniquesforfederatedlearning AT zhanghaoji surveyofdifferentialprivacytechniquesforfederatedlearning AT sunlianshan surveyofdifferentialprivacytechniquesforfederatedlearning |