An Intrusion Detection System Model in a Local Area Network using Different Machine Learning Classifiers
Asma Hulayyil Aljohani, Anas Bushnag · 2021
In recent years, local systems have become more open to the Internet, which increases the importance of secure networks. Interconnected systems are under the threat of network adversaries. An Intrusion Detection System (IDS) is one of the most powerful method that can handle computer network intrusions by monitoring unknown and suspicious activities. Moreover, an IDS can sound an alarm when an intrusion occurs and then take some actions to prevent this intrusion from spreading. An IDS should be able to distinguish the difference between an intruder and a legitimate packet by examining their behavior. To prevent security threats in a Local Area Network (LAN), the proposed system utilizes Neural Network and the Support Vector Machine (SVM) models for intrusion detection. The proposed technique is applied to the KDD99 dataset. The KDD99 is a benchmark used for anomaly-based detection. This technique identifies attacks fast and efficiently. A comparison between the performance of the SVM and Neural Network models is conducted. The results show that Neural Network performed better than all SVM kernel models regarding classification accuracy. The SVM linear kernel has a slight advantage over the SVM Gaussian kernel and much better performance than the SVM polynomial kernel.