Visible to the public Anomaly Detection in Cyber Security Attacks on Networks Using MLP Deep Learning

TitleAnomaly Detection in Cyber Security Attacks on Networks Using MLP Deep Learning
Publication TypeConference Paper
Year of Publication2018
AuthorsTeoh, T. T., Chiew, G., Franco, E. J., Ng, P. C., Benjamin, M. P., Goh, Y. J.
Conference Name2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE)
Date Publishedjul
KeywordsAdvanced Security Network Metrics \\& NonPayload-Based Obfuscations, anomaly detection, Big Data, big data security, C4.5, computer network security, Correlation, cyber security, cyber security attacks, cyber security threats, Decision trees, Deep Learning, feature extraction, ID3, Information security, invasive software, J48, learning (artificial intelligence), machine learning, Malware, malware attacks, malware data, Metrics, MLP deep learning, Multilayer Perceptron, Multilayer Perceptron (MLP), multilayer perceptrons, pubcrawl, resilience, Resiliency, Scalability, WEKA
Abstract

Malicious traffic has garnered more attention in recent years, owing to the rapid growth of information technology in today's world. In 2007 alone, an estimated loss of 13 billion dollars was made from malware attacks. Malware data in today's context is massive. To understand such information using primitive methods would be a tedious task. In this publication we demonstrate some of the most advanced deep learning techniques available, multilayer perceptron (MLP) and J48 (also known as C4.5 or ID3) on our selected dataset, Advanced Security Network Metrics & Non-Payload-Based Obfuscations (ASNM-NPBO) to show that the answer to managing cyber security threats lie in the fore-mentioned methodologies.

URLhttps://ieeexplore.ieee.org/document/8538395
DOI10.1109/ICSCEE.2018.8538395
Citation Keyteoh_anomaly_2018