The rapid development in Information and Communication Technology (ICT) has made communication to be instant and easily accessible. The enormous contributions of Internet to business transactions coupled with its ease of use has resulted in increased number of internet users and consequently, intruders. This development has generated lots of security threats on networks and data through series of network attacks. One of the most prominent network attacks is Drive-by Download Attack. Despite a series of research and applications in network intrusion detection system, there are still many challenges that bedeviled the network as a result of Drive-by download attacks. Drive-by download attacks are attacks that automatically download malwares to user's computer without his or her knowledge or consent. Drive-by Download Attacks are accomplished by exploiting web browsers and plugins vulnerabilities. Traditional security tools such as Signature-based Intrusion Detection Systems (SIDS) and Anomaly-Based Intrusion Detection Systems (AIDS) are insufficient and ineffective for detecting new attacks and most especially Drive-By Download Attacks. Deep Learning is a sub-field of Machine Learning inspired by the way biological neurons in the human brain work. In this paper, Deep Learning Approach with Convolutional Neural Network (CNN) was designed in solving the problem of detecting Drive-by Download Attack using UNSW NB15 public dataset. The results of the experiments showed that the training accuracy was 81.60%. The model achieves respectable training and validation accuracies, indicating a reasonable ability to classify drive-by downloads. The losses are moderately low, suggesting that the model's predictions are relatively accurate.

Authors: O.D. Alowolodu, A.H. Afolayan, A.G. Ola

Published in: International Conference for Internet Technology and Secured Transactions (ICITST-2024)

• Date of Conference: 4-6 November 2024
• DOI: 10.20533/ICITST.2024.0019
• ISBN: 978-1-913572-76-1
• Conference Location: St Anne’s College, Oxford University, UK