Investigating the Use of Federated Learning to Enable Collaborative AI Model Training While Preserving Data Privacy in Industrial IoT Settings.

EasyChair Preprint 13279

Abstract

The rapid growth of industrial Internet of Things (IoT) applications has led to an increased need for AI model training to extract valuable insights from vast amounts of sensor data. However, data privacy concerns arise when sensitive industrial data is shared for collaborative model training. Federated learning has emerged as a promising technique that enables collaborative AI model training while preserving data privacy in industrial IoT settings. This paper investigates the use of federated learning in industrial IoT and explores its potential to address the challenges related to data privacy.

The paper begins with an introduction to industrial IoT and the significance of AI model training in this context. It highlights the challenges associated with data privacy and introduces federated learning as a potential solution. The concept and components of federated learning are explained, along with its advantages and limitations.

The application of federated learning in industrial IoT is then explored, emphasizing the benefits it offers for AI model training. Case studies and examples are presented to demonstrate successful implementations of federated learning in industrial IoT settings.

Keyphrases: Data Security, Federated Learning, Industrial IoT, Privacy, data bias, fairness

@booklet{EasyChair:13279,
  author    = {Ayuns Luz and Harold Jonathan},
  title     = {Investigating the Use of Federated Learning to Enable Collaborative AI Model Training While Preserving Data Privacy in Industrial IoT Settings.},
  howpublished = {EasyChair Preprint 13279},
  year      = {EasyChair, 2024}}