Ce travail propose un modèle de détection d'intrusion (IDM) pour la détection des tentatives d'intrusion causées par les vers. La proposition est un IDM hybride car elle prend en compte les caractéristiques des paquets réseau et de l'hôte sensibles aux vers. L'ensemble de données HybD (Hybrid Dataset) proposé, qui est composé des fonctionnalités du jeu de données KDD'99 (Knowledge Discovery in Databases) à 10 % et des fonctionnalités basées sur l'hôte suggérées, est utilisé pour construire et tester le modèle proposé. Les approches de détection des abus et des anomalies sont utilisées. L'IDM hybride a été conçu en utilisant des méthodes d'exploration de données (DM) qui, pour leur capacité à détecter de nouvelles intrusions avec précision et automatiquement, il peut également traiter une grande quantité de données, et il est plus susceptible de découvrir les informations ignorées et cachées. Le classificateur interactif Dichotomiseur 3 (ID3) et le classificateur bayésien naïf (NB) sont utilisés pour construire et vérifier la validité du modèle proposé en termes de précision du classificateur. Les résultats de la mise en œuvre du modèle proposé montrent que la précision du classificateur NB est généralement supérieure à celle du classificateur ID3 avec les quatre ensembles de fonctionnalités.
Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.
Vendeur : BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Allemagne
Taschenbuch. Etat : Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -This work proposes an Intrusion Detection Model (IDM) for detection of intrusion attempts caused by worms. The proposal is a hybrid IDM since it considers features of both network packets and host that are sensitive to worms. The proposed HybD (Hybrid Dataset) dataset, which is composed of the 10% KDD'99 (Knowledge Discovery in Databases) dataset features and the suggested host-based features, is used to build and test the proposed model. Both of misuse and anomaly detection approaches are used. The hybrid IDM has been designed using Data Mining (DM) methods that for their ability to detect new intrusions accurately and automatically, also it can process large amount of data, and it is more likely to discover the ignored and hidden information. Interactive Dichotomizer 3 classifier (ID3) and Naïve Bayesian Classifier (NB) are used to build and verify the validity of the proposed model in term of classifier accuracy. The results of implementing the proposed model show that accuracy of NB classifier is generally higher than that of ID3 classifier with the four sets of features. 132 pp. Englisch. N° de réf. du vendeur 9783659697173
Quantité disponible : 2 disponible(s)
Vendeur : moluna, Greven, Allemagne
Etat : New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Autor/Autorin: Ali InasThis book written by Inas Ali who is an assistance lecturer at Computer Science Department in Baghdad University. She has got BcS degree in computer science from Baghdad University in 2003, and the Master degree in computer . N° de réf. du vendeur 158428838
Quantité disponible : Plus de 20 disponibles
Vendeur : buchversandmimpf2000, Emtmannsberg, BAYE, Allemagne
Taschenbuch. Etat : Neu. This item is printed on demand - Print on Demand Titel. Neuware -This work proposes an Intrusion Detection Model (IDM) for detection of intrusion attempts caused by worms. The proposal is a hybrid IDM since it considers features of both network packets and host that are sensitive to worms. The proposed HybD (Hybrid Dataset) dataset, which is composed of the 10% KDD'99 (Knowledge Discovery in Databases) dataset features and the suggested host-based features, is used to build and test the proposed model. Both of misuse and anomaly detection approaches are used. The hybrid IDM has been designed using Data Mining (DM) methods that for their ability to detect new intrusions accurately and automatically, also it can process large amount of data, and it is more likely to discover the ignored and hidden information. Interactive Dichotomizer 3 classifier (ID3) and Naïve Bayesian Classifier (NB) are used to build and verify the validity of the proposed model in term of classifier accuracy. The results of implementing the proposed model show that accuracy of NB classifier is generally higher than that of ID3 classifier with the four sets of features.VDM Verlag, Dudweiler Landstraße 99, 66123 Saarbrücken 132 pp. Englisch. N° de réf. du vendeur 9783659697173
Quantité disponible : 1 disponible(s)
Vendeur : AHA-BUCH GmbH, Einbeck, Allemagne
Taschenbuch. Etat : Neu. nach der Bestellung gedruckt Neuware - Printed after ordering - This work proposes an Intrusion Detection Model (IDM) for detection of intrusion attempts caused by worms. The proposal is a hybrid IDM since it considers features of both network packets and host that are sensitive to worms. The proposed HybD (Hybrid Dataset) dataset, which is composed of the 10% KDD'99 (Knowledge Discovery in Databases) dataset features and the suggested host-based features, is used to build and test the proposed model. Both of misuse and anomaly detection approaches are used. The hybrid IDM has been designed using Data Mining (DM) methods that for their ability to detect new intrusions accurately and automatically, also it can process large amount of data, and it is more likely to discover the ignored and hidden information. Interactive Dichotomizer 3 classifier (ID3) and Naïve Bayesian Classifier (NB) are used to build and verify the validity of the proposed model in term of classifier accuracy. The results of implementing the proposed model show that accuracy of NB classifier is generally higher than that of ID3 classifier with the four sets of features. N° de réf. du vendeur 9783659697173
Quantité disponible : 1 disponible(s)
Vendeur : preigu, Osnabrück, Allemagne
Taschenbuch. Etat : Neu. A Model To Detetct DOS Using Data Mining Classification Algorithms | Inas Ali (u. a.) | Taschenbuch | 132 S. | Englisch | 2015 | LAP LAMBERT Academic Publishing | EAN 9783659697173 | Verantwortliche Person für die EU: preigu GmbH & Co. KG, Lengericher Landstr. 19, 49078 Osnabrück, mail[at]preigu[dot]de | Anbieter: preigu. N° de réf. du vendeur 104646856
Quantité disponible : 5 disponible(s)