A syllabus on data mining and machine learning with applications to cybersecurity

Abstract

Big data analytics are very fruitful for solving problems in cybersecurity. We have analyzed modern trends in intelligent security systems research and practice and worked out a syllabus for a new university course in the area of data mining and machine learning with applications to cybersecurity. The course is for undergraduate and graduate students studying the cybersecurity. The main objective of the course is to provide students with fundamental concepts in data mining (in particular, mining frequent patterns, associations and correlations, classification, cluster analysis, outlier detection), machine learning (including neural networks, support vector machines etc.) and related issues, e.g. the basics of multidimensional statistics. Contrary to the traditional data mining and machine learning courses we illustrate course topics by cases from the area of cybersecurity including botnet detection, intrusion detection, deep packet inspection, fraud monitoring, malware detection, phishing detection, active authentication. We note that our course has great potential for development.