Intrusion detection for the Internet of Things using deep Learning techniques / Lameche, Mohamed Houssem Eddine  

Public ISBD Titre : Intrusion detection for the Internet of Things using deep Learning techniques Type de document : texte imprimé Auteurs : Lameche, Mohamed Houssem Eddine, Auteur ; Fenanir,Samir, Directeur de thèse Editeur : Setif:UFA Année de publication : 2021 Importance : 1 vol (62 f .) Format : 29 cm Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Internet of Things (IoT) Intrusion Detection System (IDS) Index. décimale : 004 Informatique Résumé : The IoT is a vast network that includes various smart devices and sensors, these "Things" collect and exchange data, but on the other hand, the risks and chances of malicious intrusions have increased and security has become a major issue in the management of corporate networks. The intrusion is any breach of security of a computer system, and to address this issue, the intrusion detection system (IDS) is widely deployed as a second block of defense when the access control fails. In this work, we present an anomaly-based IDS in the IoT environment using deep learning algorithms to design and implement technical and software architecture in an IoT context that makes its defense more effective in classifying attacks than normal use by building a semi-supervised deep autoencoder (SDEA) model which extracts the basic features of the normal use in latent content, so in the case of an attack, it compares the attack features with the normal features and because of the difference who crosses the threshold, it will be classified as an attack. Côte titre : MAI/0517 En ligne : https://drive.google.com/file/d/11IRUm3hKprY7pbEME-9U--QRbELbZgf4/view?usp=shari [...] Format de la ressource électronique : pdf Intrusion detection for the Internet of Things using deep Learning techniques [texte imprimé] / Lameche, Mohamed Houssem Eddine, Auteur ; Fenanir,Samir, Directeur de thèse . - [S.l.] : Setif:UFA, 2021 . - 1 vol (62 f .) ; 29 cm. Langues : Français (fre) Catégories : Thèses & Mémoires:Informatique Mots-clés : Internet of Things (IoT) Intrusion Detection System (IDS) Index. décimale : 004 Informatique Résumé : The IoT is a vast network that includes various smart devices and sensors, these "Things" collect and exchange data, but on the other hand, the risks and chances of malicious intrusions have increased and security has become a major issue in the management of corporate networks. The intrusion is any breach of security of a computer system, and to address this issue, the intrusion detection system (IDS) is widely deployed as a second block of defense when the access control fails. In this work, we present an anomaly-based IDS in the IoT environment using deep learning algorithms to design and implement technical and software architecture in an IoT context that makes its defense more effective in classifying attacks than normal use by building a semi-supervised deep autoencoder (SDEA) model which extracts the basic features of the normal use in latent content, so in the case of an attack, it compares the attack features with the normal features and because of the difference who crosses the threshold, it will be classified as an attack. Côte titre : MAI/0517 En ligne : https://drive.google.com/file/d/11IRUm3hKprY7pbEME-9U--QRbELbZgf4/view?usp=shari [...] Format de la ressource électronique : pdf

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
MAI/0517	MAI/0517	Mémoire	Bibliothéque des sciences	Anglais	Disponible Disponible

---

1 (1 - 1 / 1)