Federated learning: Data privacy and cyber security in edge-based machine learning

White, Jonathan; Legg, Phil

Abstract

Machine learning is now a key component of many applications for understanding trends and characteristics within the wealth of data that may be processed, whether this be learning about customer preferences and travel preferences, forecasting future behaviour of stock markets, weather, or crime rates, classifying and recognising images and text content, or a whole host of other technologies that are becoming integrated as part of our daily lives. The raft of applications is broad and continues to grow daily. At the same time, there are growing concerns about the data protection, security and data privacy of such applications, as smart devices are embedded deeper in our daily activity. How can we ensure that this data that is gathered and utilised about our daily interactions can be best protected, in terms of ensuring systems are truly secure and that users privacy is maintained and assured. In this chapter, explore the recent developments of Federated Learning, introduced by Google in 2016. This approach mandates that data remains at the place where it was collected, and that is it only data models that pass over the network. In this way, there is no centralised data storage, and no personal data leaves the point where it was generated. We present the recent works of this growing area of research, and we posit the challenges posed from both the data privacy and cyber security standpoints. We show how Federated Learning can be applied to a cyber security case study of distributed monitoring for Intrusion Detection. We also consider the wider implications of data privacy in machine learning and federated learning systems.

Citation

White, J., & Legg, P. (2023). Federated learning: Data privacy and cyber security in edge-based machine learning. In C. Hewage, Y. Rahulamathavan, & D. Ratnayake (Eds.), Data Protection in a Post-Pandemic Society (DPPPS) – Best Practices, Laws, Regulations, and Recent Solutions. Springer. https://doi.org/10.1007/978-3-031-34006-2

• Acceptance Date: Dec 19, 2022
• Online Publication Date: Jul 11, 2023
• Publication Date: Jul 12, 2023
• Deposit Date: Feb 3, 2023
• Publicly Available Date: Jul 12, 2025
• Publisher: Springer
• Series Title: Data Privacy in a Post-Pandemic Society - Best Practices, Laws, Regulations and Recent Solutions
• Book Title: Data Protection in a Post-Pandemic Society (DPPPS) – Best Practices, Laws, Regulations, and Recent Solutions
• Chapter Number: 2
• ISBN: 9783031340055
• DOI: https://doi.org/10.1007/978-3-031-34006-2
• Keywords: Federated Learning; Data Privacy; Cyber Security; Machine Learning
• Public URL: https://uwe-repository.worktribe.com/output/10360305