Intelligent Detection of Packet Drop attack in Mobile Ad-hoc Networks using Bat Metaheuristic Algorithm and Support Vector Machines

Mobile Ad-Hoc Networks (MANETs) are very attractive in terms of flexibility and there is no need for predefined communication infrastructure such as wired network. Mobile nodes can communicate and exchange information without relying on a predefined infrastructure. Characteristics of being mobile make them vulnerable to internal and external attacks. Packet deletion attack is a type of denial of service attack in which the router that is supposed to send the packets bypasses them. In this dissertation, a method for investigating the possible intrusion characteristics in a system based on the evolution of the bat algorithm method and then the Support Vector Machine (SVM) classifier for detecting packet removal attack in mobile case networks is presented. After feature extraction, a feature selection system is presented with the aim of eliminating ineffective features based on combining the bat algorithm with the statistical target function and then classifying the network access records with the aim of separating the attacks with the backup machine classifier. The results show that our proposed method has less packet crashes compared to previous studies. This is due to the fact that in the proposed method, the use of backup vector machine classifier can be able to effectively identify and isolate attacks.

Intelligent Detection of Packet Drop attack in Mobile Ad-hoc Networks using Bat Metaheuristic Algorithm and Support Vector Machines Keywords:

MANET , Attack detection , Packet drop attack , Bat algorithm , Support vector machine