Software Engineering Institute

The currency of cybersecurity is information, and nowhere is information more prevalent than modern computer networks. Every day, our critical infrastructure generates enormous amounts of data, more than can possibly be reviewed manually. Extracting valuable insights from this data requires unique, customized tooling. The field of Data Science focuses on creating techniques to uncover hidden patterns in enormous data sets, and developing tooling to enable this discovery on any data set, in any environment. Over the past few years, significant advances have been made in both methodology and tooling, enabling even the most subtle of patterns to be identified using modern computer power. The August 2017 CERT Data Science and Cybersecurity Symposium in Arlington, Virginia, highlighted these advances, reviewed a number of government use cases where data science has been used to great effect, and provided a demonstration of the capabilities that these tools can provide.