Distributed machine learning and multi-agent systems for enhanced attack detection and resilience in iot networks

Funchal, Gustavo Silva; Pedrosa, Tiago; Prieta, Fernando de la; Leitão, Paulo

http://hdl.handle.net/10198/36502

Utilize este identificador para referenciar este registo.

Nome:	Descrição:	Tamanho:	Formato:
131544.pdf		1.18 MB	Adobe PDF	Ver/Abrir

Contacte-nos

Autores

Funchal, Gustavo Silva

Pedrosa, Tiago

Prieta, Fernando de la

Leitão, Paulo

Resumo(s)

The exponential growth of connected devices, including sensors, mobile devices, and various Internet of Things (IoT) devices, has resulted in a substantial increase in data generation. Traditionally, data analysis involves transferring data to cloud computing systems, leading to latency issues and excessive network traffic. Edge computing emerges as a promising solution by bringing processing closer to the data sources. However, edge computing faces challenges, particularly in terms of limited computational power, which can create constraints in the execution of machine learning (ML) tasks. This paper aims to analyze strategies for distributing ML tasks among multiple nodes based on multi-agent systems (MAS) technology to have a collaborative approach and compare these strategies to provide an overview of best practices for achieving the optimal performance in intrusion detection for Industrial Internet of Things (IIoT). In this way, the well-known CICIoT2023 data set was used, and centralized and distributed ML techniques were implemented, and evaluated. The distributed edge ML approach achieved promising results, presenting an improvement of between 7.73% and 32.18% in the correction of wrong predictions of detection of attacks on IoT devices, significantly improving the precision and recall of the applied techniques.

Palavras-chave

Intrusion Detection Systems Multi-Agent Systems Internet of Things Machine Learning

URI

http://hdl.handle.net/10198/36502

Citação

Funchal, Gustavo Silva; Pedrosa, Tiago; Prieta, Fernando de la; Leitão Paulo (2025). Distributed machine learning and multi-agent systems for enhanced attack detection and resilience in iot networks. In the 11th International Conference on Information Systems Security and Privacy. Porto, Portugal. 2, p. 192-203. ISSN 2184-4356. DOI: 10.5220/0013154400003899