From distributed machine learning to federated learning: In the view of data privacy and security

Abstract

Federated learning is an improved version of distributed machine learning that further offloads operations which would usually be performed by a central server. The server becomes more like an assistant coordinating clients to work together rather than micromanaging the workforce as in traditional DML. One of the greatest advantages of federated learning is the additional privacy and security guarantees it affords.Federated learning architecture relies on smart devices, such as smartphones and IoT sensors, that collect and process their own data, so sensitive information never has to leave the client device. Rather, clients train a submodel locally and send an encrypted update to the central server for aggregation into the global model. These strong privacy guarantees make federated learning an attractive choice in a world where data breaches and information theft are common and serious threats. This survey outlines the landscape and latest developments in data privacy and security for federated learning. We identify the different mechanisms used to provide privacy and security, such as differential privacy, secure multiparty computation and secure aggregation.We also survey the current attack models, identifying the areas of vulnerability and the strategies adversaries use to penetrate federated systems. The survey concludes with a discussion on the open challenges and potential directions of future work in this increasingly popular learning paradigm.

Reinforcement Learning for Edge Device Selection Using Social Attribute Perception in Industry 4.0

“…Literature [16] introduces federated learning to the public for the first time, which is a decentralized machine learning for model training through mobile devices. Following the literature [16], scholars have mainly conducted research on improving the security of the federated learning protocol [17], [18]. However, the methods in these literatures mainly aim at minimizing the computational overhead or time of general computing tasks, and do not fundamentally improve the efficiency of model training.…”

Distributed Learning Applications in Power Systems: A Review of Methods, Gaps, and Challenges

“…Another key difference is that clients in federated learning are also data generation nodes (smartphones, sensors, etc.) while the clients in distributed learning are only processing units [42]. Figure 2 shows the federated learning scheme.…”

The More, the Better? A Study on Collaborative Machine Learning for DGA Detection

“…The FL paradigm was proposed to enhance the data privacy for participants by reducing the exposure of their data. This alone is not sufficient, as attacks still threaten data privacy in FL [29,46].…”