Network intrusions classification using data mining approaches

• Main Authors: Slamet, Slamet, Izzeldin, Ibrahim Mohamed
• Format: Article
• Language: English
• Published: JATIT 2021
• Subjects: QA75 Electronic computers. Computer science; T Technology (General)
• Online Access: http://umpir.ump.edu.my/id/eprint/37961/1/Network%20intrusions%20classification%20using%20data%20mining%20approaches.pdf; http://umpir.ump.edu.my/id/eprint/37961/; http://www.jatit.org/volumes/Vol99No7/17Vol99No7.pdf

Intrusion Detection System has an important task in detecting threats or attacks in the computer networks. Intrusion Detection System (IDS) is a network protection device used to identify and check data packets in network traffic. Snort is free software used to detect attacks and protect computer networks. Snort can only detect misuse attacks, whereas to detect anomaly attacks using Bayes Network, Naive Bayes, Random Tree, LMT and J-48 Classification Method. In this paper, the experimental study uses the KDDCUP 99 dataset and the dataset taken from Campus Network. The main objective of this research is to detect deceptive packets that pass computer network traffic. The steps taken in this study are data preparation, data cleaning, dataset classification, feature extraction, rules snort for detecting, and detecting packet as an attack or normal. The result of the proposed system is an accurate detection rate.