Machine Learning in Cyber-Security - Problems, Challenges and Data Sets

TL;DR

This paper discusses key cyber-security challenges, introduces new data sets for research, and proposes a pivoting-based labeling method to address label scarcity in machine learning applications.

Contribution

It provides novel cyber-security data sets and a pivoting technique for labeling, facilitating research in machine learning solutions for security problems.

Findings

New cyber-security data sets for research

A pivoting-based labeling method to address label scarcity

Enhanced tools for machine learning in cyber-security

Abstract

We present cyber-security problems of high importance. We show that in order to solve these cyber-security problems, one must cope with certain machine learning challenges. We provide novel data sets representing the problems in order to enable the academic community to investigate the problems and suggest methods to cope with the challenges. We also present a method to generate labels via pivoting, providing a solution to common problems of lack of labels in cyber-security.