Federated Learning for Network Intrusion Detection in Ambient Assisted Living Environments

Given the Internet of Things rapid expansion and widespread adoption, it is of great concern to establish secure interaction between devices without worsening the quality of their performance. Using machine learning techniques has been shown to improve detecting anomalous behavior in these types of networks, but their implementation leads to poor performance and compromised privacy. To better address these shortcomings, federated learning is being introduced. It enables devices to collaboratively train and evaluate a shared model while keeping personal data on-site (e.g., smart homes, intensive care units, hospitals, etc.), thus minimizing the possibility of an attack and fostering real-time distribution of models and learning. The paper investigates the performance of federated learning in comparison to deep learning, with respect to network intrusion detection in ambient assisted living environments. The results demonstrate comparable performances of federated learning with deep learning, while achieving improved data privacy and security.