Depot Institutionnel de l'UMBB >
Mémoires de Master 2 >
Institut de Génie Electrique et d'Electronique >
Computer >
Veuillez utiliser cette adresse pour citer ce document :
http://dlibrary.univ-boumerdes.dz:8080/handle/123456789/12634
|
Titre: | Machine learning-based approaches for intrusion detection |
Auteur(s): | Kezzoula, Soulef Mohammed Sahnoun, A. (Supervisor) |
Mots-clés: | Machine learning Intrusion detection |
Date de publication: | 2023 |
Editeur: | Université M’hamed Bougara de Boumerdes : Institut de Genie Electrique et Electronique |
Résumé: | The rapid increase in network security threats necessitates the development of effec-
tive intrusion detection model capable of identifying and mitigating malicious activities.
This approach presents the development and evaluation of an intrusion detection model
utilizing various machine learning algorithms that provide a potential pathway for at-
tacks detection. The model is designed to detect and mitigate malicious activities within
a network environment. To train and test the machine learning models, a comprehensive
dataset sourced from Kaggle is employed, encompassing a wide range of attack scenarios
and normal network behaviors. The models are evaluated using classificatio nevaluation
metrics such as accuracy, precision, and recall, demonstrating their capability to accu-
rately classify instances and identify potential threats. The primary objective of this
approach is to enhance the detection of attacks irrespective of their types, while minimiz-
ing the occurrence of false positives. The results obtained highlight the effectivenes sof
the intrusion detection model in providing a proactive network security solution, enabling
timely detection and response to malicious activities. The finding so fthi sprojec tcon-
tribute to the fiel do fintrusio ndetection ,pavin gth ewa yfo rimprove dsecurit ymeasures
in network environments. |
Description: | 66p. |
URI/URL: | http://dlibrary.univ-boumerdes.dz:8080/handle/123456789/12634 |
Collection(s) : | Computer
|
Fichier(s) constituant ce document :
|
Tous les documents dans DSpace sont protégés par copyright, avec tous droits réservés.
|