Dos and Don'ts of Machine Learning in Computer Security

TL;DR

This paper critically examines the use of machine learning in computer security, highlighting common pitfalls, analyzing recent literature, and offering practical recommendations to improve research quality and application reliability.

Contribution

It identifies widespread pitfalls in security-focused machine learning research, empirically demonstrates their impact, and proposes actionable guidelines to enhance future work.

Findings

Pitfalls are common in security ML research

Individual pitfalls can lead to unrealistic performance claims

Recommendations can help mitigate identified issues

Abstract

With the growing processing power of computing systems and the increasing availability of massive datasets, machine learning algorithms have led to major breakthroughs in many different areas. This development has influenced computer security, spawning a series of work on learning-based security systems, such as for malware detection, vulnerability discovery, and binary code analysis. Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance and render learning-based systems potentially unsuitable for security tasks and practical deployment. In this paper, we look at this problem with critical eyes. First, we identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We conduct a study of 30 papers from top-tier security conferences within the past 10 years, confirming that these pitfalls are widespread in the current security literature. In an empirical analysis, we further demonstrate how individual pitfalls can lead to unrealistic performance and interpretations, obstructing the understanding of the security problem at hand. As a remedy, we propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible. Furthermore, we identify open problems when applying machine learning in security and provide directions for further research.