Increasing the Performance of an IDS using ANN model on the realistic cyber dataset CSE-CIC-IDS2018
Yassine Ayachi, Youssef Mellah, Jamal Berrich, Toumi Bouchentouf · 2020
Our society, economy, and critical infrastructures have become largely dependent on computer networks and information technology solutions, on the other hand, cyber-attacks are becoming more sophisticated and thereby presenting increasing challenges in accurately detecting intrusions. Failure to prevent the intrusions could degrade the credibility of security services, e.g. data integrity, confidentiality, and availability. Different detection methods have been proposed to tackle computer security threats, which can be broadly classified into Anomaly-based Intrusion Detection Systems (AIDS) and Signature-based Intrusion Detection Systems (SIDS). One of the most preferred protection mechanisms is the machine learning based IDS which provide the most relevant results ever, but it still suffers from disadvantages like unrepresentative Dataset (the most of them were collected during a limited period of time in some specific networks and generally don’t contain up-to-date data). Additionally, they are imbalanced and do not hold sufficient data for all types of attack. These imbalanced and outdated datasets decrease the efficiency of current IDS, especially for new attack types. Some recent works proposed many machine-learning-based IDS based on an up-to-date security dataset CSE-CIC-IDS2018, in this paper we propose an experimental approach of Artificial Neural Networks with adapted hyper-parameters. Experimental results demonstrated that the proposed approach considerably improve the general accuracy.