Dos and Don'ts of Machine Learning in Computer Security

Authors: 

Daniel Arp, Technische Universität Berlin; Erwin Quiring, Technische Universität Braunschweig; Feargus Pendlebury, King's College London and Royal Holloway, University of London and The Alan Turing Institute; Alexander Warnecke, Technische Universität Braunschweig; Fabio Pierazzi, King's College London; Christian Wressnegger, KASTEL Security Research Labs and Karlsruhe Institute of Technology; Lorenzo Cavallaro, University College London; Konrad Rieck, Technische Universität Braunschweig

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.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {277204,
title = {Dos and Don{\textquoteright}ts of Machine Learning in Computer Security},
booktitle = {31st USENIX Security Symposium (USENIX Security 22)},
year = {2022},
address = {Boston, MA},
url = {https://www.usenix.org/conference/usenixsecurity22/presentation/arp},
publisher = {USENIX Association},
month = aug,
}