Differentially Private Federated Learningfor Anomaly Detection in eHealth Networks

Abstract

Increasing number of ubiquitous devices are being used in the medical field to collect patient information. Those connected sensors can potentially be exploited by third parties who want to misuse personal information and compromise the security, which could ultimately result even in patient death. This paper addresses the security concerns in eHealth networks and suggests a new approach to dealing with anomalies. In particular we propose a concept for safe in-hospital learning from internet of health things (IoHT) device data while securing the network traffic with a collaboratively trained anomaly detection system using federated learning. That way, real time traffic anomaly detection is achieved, while maintaining collaboration between hospitals and keeping local data secure and private. Since not only the network metadata, but also the actual medical data is relevant to anomaly detection, we propose to use differential privacy (DP) for providing formal guarantees of the privacy spending accumulated during the federated learning. CCS CONCEPTS• Security and privacy → Intrusion detection systems; • Applied computing → Health care information systems; • Computing methodologies → Anomaly detection; Distributed artificial intelligence.

Göwfeda Novel Federated Network Intrusion Detection System

“…The reason for AEs being so common within FL-IDS architecture 7,11,38,39,44 is that their input reconstruction abilities suit themselves very nicely for intrusion detection based on anomaly detection. Once the usual network traffic patterns are learned, anomalies are translated into high reconstruction loss instances.…”

A review of Federated Learning in Intrusion Detection Systems for IoT

“…[91], [92], [93], [94] [95], [96], [97], [98] [99], [100], [101], [102], [103] [104], [105], [106], [107], [108] Fig. 2: Existing Deep Learning Federated Intrusion Detection Systems by model architecture.…”

“…Moreover, autoencoder based FL-IDS could be extended to other areas of edge computing. For instance, Cholakoska et al [101] leverage FL to deal with anomalies in eHealth networks. Due to the sensitive nature of medical data, employing Differential Privacy gains special attention in this work.…”

eHealth: A Survey of Architectures, Developments in mHealth, Security Concerns and Solutions

“…As a novel technique, it was tested and found to outperform existing methods against relevant threat models. Machine learning approaches, such as in [ 189 ], are also beginning to come to the fore against security attacks in eHealth networks. For instance, in [ 189 ], the authors developed a differentially private federated learning method for anomaly detection in eHealth networks.…”

“…Machine learning approaches, such as in [ 189 ], are also beginning to come to the fore against security attacks in eHealth networks. For instance, in [ 189 ], the authors developed a differentially private federated learning method for anomaly detection in eHealth networks. In this case, network traffic was protected using a federated learning-based jointly trained anomaly detection system.…”