Lightweight Federated Learning Based Detection of Malicious Activity in Distributed Networks

Wöhnert, Kai HendrikStolzenburg, Frieder2023-09-202023-09-202023https://dl.gi.de/handle/20.500.12116/42400In an increasingly complex cyber threat landscape, traditional malware detection methods often fall short, particularly within resource-limited distributed networks like smart grids. This research project aims to develop an efficient malware detection system for such distributed networks, focusing on three elements: feature extraction, feature selection, and classification. For classification, a lightweight and accurate machine-learning model needs to be developed.enmachine learning; malware classification; intrusion detectionLightweight Federated Learning Based Detection of Malicious Activity in Distributed NetworksText10.18420/ki2023-dc-12