Evaluation of Deep Learning Algorithms for Intelligent Intrusion Detection Systems

Main Article Content

Bandar T. Alshammari, Dr.FaeizAlserhani, Dr.AmjadAlsirhani

Abstract

Besides the vast increase of using the internet, network security is one of the major concerns nowadays. Intrusion
Detection System (IDS) has been an effective way for achieving security to detect malicious activities. Moreover, it plays a
vital role in ensuring information and network security. However, performance and effective IDS have remained a significant
issue for IDS. In this research, we will explore how to model an intrusion detection system based on deep learning as an
effective approach to detect malicious behaviour either previously known or zero-day attack in communication networks. A
CICIDS2017 dataset was used to evaluate the model performance and find the optimized regularization. The performance of
the proposed model was evaluated on different sets of the dataset. The result shows that the number of neurons and different
learning rates impacts the performance of the proposed model.

Article Details

Section
Articles