Abstract

Deep learning has seen considerable success in several application sectors. Unfortunately, little research has been done on its efficacy in the context of network intrusion detection. This article includes case studies that use deep learning to identify network anomalies both supervised and unsupervised. It has been demonstrated that deep neural networks (DNNs) outperform current machine learning-based intrusion detection systems in the presence of shifting IP addresses. We also demonstrate how auto encoders can support network anomaly detection.

References

1. Mariam Aljouhi and Sara Al Hosani. Windows Forensics Analysis. EJPSS. 2022. Vol. 1(1):4-11. DOI: 10.54878/EJPSS.179
2. Riktesh Srivastava. Service Quality Control using Queuing Theory. EJBESS. 2022. Vol. 1(1):31-38. DOI: 10.54878/EJBESS.169
3. Tobias Haschke, Mathias Hüsing and Burkhard Corves. Bots2ReC - Analysis of Key Findings for the Application Development of Semi-Autonomous Asbestos Removal. IJADT. 2022. Vol. 1(1):4-12. DOI: 10.54878/IJADT.166
4. Tosin Ekundayo and Osama Isaac. Open Data: A National Data Governance Strategy for Open Science and Economic Development - A case study of the United Arab Emirates. EJBESS. 2023. Vol. 1(2):98-109. DOI: 10.54878/EJBESS.208