Dos and Don'ts of Machine Learning in Computer Security

Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Christian Wressnegger, Konrad Rieck

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

164 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationDos and Don'ts of Machine Learning in Computer Security
Publication statusAccepted/In press - 15 Jul 2021

Publication series

NameUsenix Security Symposium (USENIX)


Dive into the research topics of 'Dos and Don'ts of Machine Learning in Computer Security'. Together they form a unique fingerprint.

Cite this