De Vivo, Simona (2025) Enhancing Internet of Things Security: Developing and Validating Sustainable Intrusion Detection Strategies. [Tesi di dottorato]
![[thumbnail of DeVivo_PhDThesis_ITEE37.pdf]](https://www.fedoa.unina.it/style/images/fileicons/other.png "DeVivo_PhDThesis_ITEE37.pdf") |
Documento PDF
DeVivo_PhDThesis_ITEE37.pdf Visibile a [TBR] Amministratori dell'archivio Download (23MB) | Richiedi una copia |
| Tipologia del documento: | Tesi di dottorato |
|---|---|
| Lingua: | English |
| Titolo: | Enhancing Internet of Things Security: Developing and Validating Sustainable Intrusion Detection Strategies |
| Autori: | Autore Email De Vivo, Simona simona.devivo@unina.it |
| Data: | 25 Febbraio 2025 |
| Numero di pagine: | 180 |
| Istituzione: | Università degli Studi di Napoli Federico II |
| Dipartimento: | Ingegneria Elettrica e delle Tecnologie dell'Informazione |
| Dottorato: | Information technology and electrical engineering |
| Ciclo di dottorato: | 37 |
| Coordinatore del Corso di dottorato: | nome email Russo, Stefano stefano.russo@unina.it |
| Tutor: | nome email Cotroneo, Domenico [non definito] |
| Data: | 25 Febbraio 2025 |
| Numero di pagine: | 180 |
| Parole chiave: | Internet of Things, Intrusion Detection System, GreenAI, Federated Learning, Cybersecurity, Sustainability |
| Settori scientifico-disciplinari del MIUR: | Area 01 - Scienze matematiche e informatiche > INF/01 - Informatica Area 09 - Ingegneria industriale e dell'informazione > ING-INF/05 - Sistemi di elaborazione delle informazioni |
| Informazioni aggiuntive: | La sottoscritta, Simona De Vivo, autrice della tesi "Enhancing Internet of Things Security: Developing and Validating Sustainable Intrusion Detection Strategies" appartiene al 37° ciclo di dottorato ITEE. Tuttavia, a causa di un problema tecnico del sito fedOAtd, ha dovuto selezionare il 36° ciclo anziché il corretto 37°. |
| Depositato il: | 27 Feb 2025 14:37 |
| Ultima modifica: | 12 Ago 2026 05:38 |
| URI: | https://www.fedoa.unina.it/id/eprint/16690 |
Abstract
This PhD thesis tackles significant cybersecurity challenges posed by the IoT, a key element of Industry 4.0 that enables real-time communication between devices. The rapid growth of IoT systems, including resource-constrained devices, renders them vulnerable to sophisticated attacks like DoS and DDoS. Traditional security solutions, such as rule-based IDS and SIEM struggle to address these challenges, particularly in the context of Industry 5.0's sustainability goals, so this work aims to develop innovative, lightweight cybersecurity strategies tailored to IoT environments. A first contribution, obtained in collaboration with Digital Platforms S.p.A. company, includes a comparative evaluation of RTA and LimaCharlie SIEMs, revealing their limitations against sophisticated DDoS attacks. This analysis points to the need for ML techniques to enhance detection accuracy. For this reason, this work proposes a lightweight IDS using K-Means clustering, achieving 90% accuracy with only 1.5W power consumption to detect DoS attacks in onboard train networks. Additionally, this dissertation introduces DDoShield-IoT, developed at the University of North Carolina at Charlotte, an IDS testbed for developing IoT-tailored security solutions. This framework generates realistic traffic patterns, allowing to address the scarcity of high-quality IoT datasets through a Data Augmentation strategy that combines real and synthetic data. Lastly, to address privacy and sustainability, this thesis presents a novel intrusion detection methodology that blends User Profiling with FL, improving intrusion detection while reducing energy consumption. This approach proved effective in the real-world scenarios of the European CyberSEAS project aimed at protecting Smart Grid infrastructures. These contributions address current IoT security limitations and align with the principles of Industry 5.0.
Downloads
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
