Titre : |
Intrusion detection for the Internet of Things using deep learning techniques |
Type de document : |
texte imprimé |
Auteurs : |
nour el imene Lakabi, Auteur ; Heithem Zeroual, Auteur ; Samir Fenanir, Directeur de thèse |
Année de publication : |
2023 |
Importance : |
1 vol (69 f .) |
Format : |
29cm |
Langues : |
Anglais (eng) |
Catégories : |
Thèses & Mémoires:Informatique
|
Mots-clés : |
Internet of Things (IoT)
intrusion detection |
Index. décimale : |
004 Informatique |
Résumé : |
In response to the increasing concerns about security in the Internet of Things (IoT), this study focuses on addressing the crucial issue of intrusion detection using deep learning techniques. The primary goal is to develop effective and reliable intrusion detection systems capable of accurately identifying intrusions in IoT networks. The research begins by providing an in-depth introduction to the IoT, encompassing its architecture, data flow, components, and application areas. Key challenges faced by the IoT, including security, interoperability, scalability, and energy efficiency, are highlighted. Emphasis is placed on the importance of IoT security, vulnerabilities, and the various types of attacks that can occur. Intrusion Detection Systems (IDS), such as signature-based, anomaly-based, and specification-based IDS, are introduced as essential tools for detecting and mitigating intrusions. The thesis presents the implementation of three deep learning-based intrusion detection programs (DNN, CNN, and RNN) using the PyTorch library, with the effectiveness of these programs evaluated using the IoTID20 dataset. By harnessing deep learning techniques, this research contributes to enhancing the understanding and effectiveness of intrusion detection in IoT networks. |
Côte titre : |
MAI/0707 |
En ligne : |
https://drive.google.com/file/d/1m2FHecjMZFFPzXSDnF_pmOhCPeKjSQYh/view?usp=drive [...] |
Format de la ressource électronique : |
pdf |
Intrusion detection for the Internet of Things using deep learning techniques [texte imprimé] / nour el imene Lakabi, Auteur ; Heithem Zeroual, Auteur ; Samir Fenanir, Directeur de thèse . - 2023 . - 1 vol (69 f .) ; 29cm. Langues : Anglais ( eng)
Catégories : |
Thèses & Mémoires:Informatique
|
Mots-clés : |
Internet of Things (IoT)
intrusion detection |
Index. décimale : |
004 Informatique |
Résumé : |
In response to the increasing concerns about security in the Internet of Things (IoT), this study focuses on addressing the crucial issue of intrusion detection using deep learning techniques. The primary goal is to develop effective and reliable intrusion detection systems capable of accurately identifying intrusions in IoT networks. The research begins by providing an in-depth introduction to the IoT, encompassing its architecture, data flow, components, and application areas. Key challenges faced by the IoT, including security, interoperability, scalability, and energy efficiency, are highlighted. Emphasis is placed on the importance of IoT security, vulnerabilities, and the various types of attacks that can occur. Intrusion Detection Systems (IDS), such as signature-based, anomaly-based, and specification-based IDS, are introduced as essential tools for detecting and mitigating intrusions. The thesis presents the implementation of three deep learning-based intrusion detection programs (DNN, CNN, and RNN) using the PyTorch library, with the effectiveness of these programs evaluated using the IoTID20 dataset. By harnessing deep learning techniques, this research contributes to enhancing the understanding and effectiveness of intrusion detection in IoT networks. |
Côte titre : |
MAI/0707 |
En ligne : |
https://drive.google.com/file/d/1m2FHecjMZFFPzXSDnF_pmOhCPeKjSQYh/view?usp=drive [...] |
Format de la ressource électronique : |
pdf |
|