Network Attack Detection using Machine Learning

Abstract

Network attack detection system is utilized to find the anomalies with the aim of finding hackers before they make immense damage to our system. Nowadays business environments need high level security because there are a lot of transactions happening in and around, even if the traditional methods fail to detect the anomalies intrusion detection system interpret a safeguard. These intrusion detection systems use alarms to inform whether there is malicious activity or not. These intrusion detection systems ought to be fine-tuned in such a way that they don't give any false alarms. It is moreover similar to firewall but there is a difference between them, firewall only blocks the intrusion from outside but it won't stop the attacks which are within the same network, Intrusion detection systems are used for this purpose. We have used a few of the Machine Learning (ML) procedures such as Support vector Machine (SVM), Decision Tree (DT), Logistic regression (LR), Random Forest (RF) and Naive Bayes (NB). For Training and classifying various abnormalities, KDD-CUP99 dataset is utilized.