The rate at which normal traffic is misclassified as being malicious.
Published in Chapter:
Threat Detection in Cyber Security Using Data Mining and Machine Learning Techniques
Daniel Kobla Gasu (Department of Computer Science, University of Ghana, Ghana)
Copyright: © 2020
|Pages: 20
DOI: 10.4018/978-1-7998-3149-5.ch015
Abstract
The internet has become an indispensable resource for exchanging information among users, devices, and organizations. However, the use of the internet also exposes these entities to myriad cyber-attacks that may result in devastating outcomes if appropriate measures are not implemented to mitigate the risks. Currently, intrusion detection and threat detection schemes still face a number of challenges including low detection rates, high rates of false alarms, adversarial resilience, and big data issues. This chapter describes a focused literature survey of machine learning (ML) and data mining (DM) methods for cyber analytics in support of intrusion detection and cyber-attack detection. Key literature on ML and DM methods for intrusion detection is described. ML and DM methods and approaches such as support vector machine, random forest, and artificial neural networks, among others, with their variations, are surveyed, compared, and contrasted. Selected papers were indexed, read, and summarized in a tabular format.