Visible to the public Performance Analysis on Denial of Service attack using UNSW-NB15 Dataset

TitlePerformance Analysis on Denial of Service attack using UNSW-NB15 Dataset
Publication TypeConference Paper
Year of Publication2021
AuthorsEdzereiq Kamarudin, Imran, Faizal Ab Razak, Mohd, Firdaus, Ahmad, Izham Jaya, M., Ti Dun, Yau
Conference Name2021 International Conference on Software Engineering Computer Systems and 4th International Conference on Computational Science and Information Management (ICSECS-ICOCSIM)
Date Publishedaug
Keywordscompositionality, cyberattack, DoS, feature extraction, filtering theory, Information management, Intrusion detection, Malware, Network security, Performance analysis, Predictive Metrics, pubcrawl, Resiliency, Scientific computing, Scientific Computing Security, UNSW-NB15
AbstractWith the advancement of network technology, users can now easily gain access to and benefit from networks. However, the number of network violations is increasing. The main issue with this violation is that irresponsible individuals are infiltrating the network. Network intrusion can be interpreted in a variety of ways, including cyber criminals forcibly attempting to disrupt network connections, gaining unauthorized access to valuable data, and then stealing, corrupting, or destroying the data. There are already numerous systems in place to detect network intrusion. However, the systems continue to fall short in detecting and counter-attacking network intrusion attacks. This research aims to enhance the detection of Denial of service (DoS) by identifying significant features and identifying abnormal network activities more accurately. To accomplish this goal, the study proposes an Intrusion Analysis System for detecting Denial of service (DoS) network attacks using machine learning. The accuracy rate of the proposed method using random forest was demonstrated in our experimental results. It was discovered that the accuracy rate with each dataset is greater than 98.8 percent when compared to traditional approaches. Furthermore, when features are selected, the detection time is significantly reduced.
DOI10.1109/ICSECS52883.2021.00083
Citation Keyedzereiq_kamarudin_performance_2021