Big Data Analytics in Cyber Security: Network Traffic and Attacks
Lidong Wang, Randy Jones
Abstract
Network attacks, intrusion detection, and intrusion prevention are important topics in cyber security. Network flows and system events generate big data, which often leads to challenges in intrusion detection with high efficiency and good accuracy. This paper focuses on the ‘Volume’, ‘Veracity’, and ‘Variety’ of big data characteristics in network traffic and attacks. Datasets with various data types including numerical data and categorical data (such as status or flag data) are analyzed with the help of R language and its functions. Data duplicates detection and removal, missing values detection, and data quality analysis are also performed. The analysis of masquerades for various users is conducted. In addition, the correlation analysis of variables and a clustering analysis based on k-means are also performed.