Privacy-Preserving Federated Learning Using Homomorphic Encryption

Park, Jaehyoung; Lim, Hyuk

doi:10.3390/app12020734

Cited by 98 publications

(34 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [113], [114], the authors proposed privacy preserving multi-party machine learning based on federated learning and homomorphic encryption where each node has a different HE private key in the same FL-based system. In [115], the authors proposed a privacy-preserving FL approach which use a momentum gradient decent optimization algorithm (MGD) to accelerate the model convergence rate during the training process.…”

Section: B Homomorphic Encryptionmentioning

confidence: 99%

A Survey and Guideline on Privacy Enhancing Technologies for Collaborative Machine Learning

et al. 2022

View full text Add to dashboard Cite

As machine learning and artificial intelligence (ML/AI) are becoming more popular and advanced, there is a wish to turn sensitive data into valuable information via ML/AI techniques revealing only data that is allowed by concerned parties or without revealing any information about the data to third parties. Collaborative ML approaches like federated learning (FL) help tackle these needs and concerns, bringing a way to use sensitive data without disclosing critically sensitive features of that data. In this paper, we provide a detailed analysis of state of the art for collaborative ML approaches from a privacy perspective. A detailed threat model and security and privacy considerations are given for each collaborative method. We deeply analyze Privacy Enhancing Technologies (PETs), covering secure multi-party computation (SMPC), homomorphic encryption (HE), differential privacy (DP), and confidential computing (CC) in the context of collaborative ML. We introduce a guideline on the selection of the privacy preserving technologies for collaborative ML and privacy practitioners. This study constitutes the first survey to provide an indepth focus on collaborative ML requirements and constraints for privacy solutions while also providing guidelines on the selection of PETs.

show abstract

Section: B Homomorphic Encryptionmentioning

confidence: 99%

A Survey and Guideline on Privacy Enhancing Technologies for Collaborative Machine Learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Using the HE scheme, the proposed privacy-preserving federated learning (PPFL) algorithm enables a centralized server to aggregate encrypted local model parameters without decryption. Furthermore, the proposed algorithm allows each node to use a different HE private key in the same FL-based system using a distributed cryptosystem [1].…”

Section: The Papersmentioning

confidence: 99%

Special Issue on Cryptography and Its Applications in Information Security

2022

View full text Add to dashboard Cite

show abstract

“…The approach ensures that analysts and researchers have benefited from the list of its applications and settings available. The focus included also provides that direct access is available [15]. Direct access means that users will not lose any essential data or time when using the system model [12].…”

Section: Privacy Principles For Learning and Analyticsmentioning

confidence: 99%

Untitled

2022

IJSEA

View full text Add to dashboard Cite

There has been tremendous growth in the field of AI and machine learning. The developments across these fields have resulted in a considerable increase in other FinTech fields. Cyber security has been described as an essential part of the developments associated with technology. Increased cyber security ensures that people remain protected, and that data remains safe. New methods have been integrated into developing AI that achieves cyber security. The data analysis capabilities of AI and its cyber security functions have ensured that privacy has increased significantly. The ethical concept associated with data privacy has also been advocated across most FinTech regulations. These concepts and considerations have all been engaged with the need to achieve the required ethical requirements. The concept of federated learning is a recently developed measure that achieves the abovementioned concept. It ensured the development of AI and machine learning while keeping privacy in data analysis. The research paper effectively describes the issue of federated learning for confidentiality. It describes the overall process associated with its development and some of the contributions it has achieved. The widespread application of federated learning in FinTech is showcased, and why federated learning is essential for overall growth in FinTech.

show abstract

Privacy-Preserving Federated Learning Using Homomorphic Encryption

Cited by 98 publications

References 17 publications

A Survey and Guideline on Privacy Enhancing Technologies for Collaborative Machine Learning

A Survey and Guideline on Privacy Enhancing Technologies for Collaborative Machine Learning

Special Issue on Cryptography and Its Applications in Information Security

Untitled

Contact Info

Product

Resources

About