Are Machine Learning Models for Malware Detection Ready for Prime Time?

Lorenzo Cavallaro; Johannes Kinder; Feargus Pendlebury; Fabio Pierazzi; Fabio Massacci; Eric Bodden; Antonino Sabetta

doi:10.1109/MSEC.2023.3236543

Are Machine Learning Models for Malware Detection Ready for Prime Time?

Lorenzo Cavallaro
, Johannes Kinder^*
, Feargus Pendlebury
, Fabio Pierazzi
, Fabio Massacci
, Eric Bodden
, Antonino Sabetta

^*Corresponding author for this work

Research output: Contribution to Journal › Article › Academic › peer-review

141 Downloads (Pure)

Abstract

We investigate why the performance of machine learning models for malware detection observed in a lab setting often cannot be reproduced in practice. We discuss how to set up experiments mimicking a practical deployment and how to measure the robustness of a model over time.

Original language	English
Pages (from-to)	53-56
Number of pages	4
Journal	IEEE Security and Privacy
Volume	21
Issue number	2
Early online date	14 Apr 2023
DOIs	https://doi.org/10.1109/MSEC.2023.3236543
Publication status	Published - Apr 2023

Bibliographical note

Publisher Copyright:
© 2003-2012 IEEE.

Access to Document

10.1109/MSEC.2023.3236543

Are_Machine_Learning_Models_for_Malware_Detection_Ready_for_Prime_TimeFinal published version, 1 MBLicence: Article 25fa Dutch Copyright Act

Persistent URL (handle)

Persistent link

Cite this

@article{021c7e334ff244a1a1c1ccb0fe339b13,

title = "Are Machine Learning Models for Malware Detection Ready for Prime Time?",

abstract = "We investigate why the performance of machine learning models for malware detection observed in a lab setting often cannot be reproduced in practice. We discuss how to set up experiments mimicking a practical deployment and how to measure the robustness of a model over time.",

author = "Lorenzo Cavallaro and Johannes Kinder and Feargus Pendlebury and Fabio Pierazzi and Fabio Massacci and Eric Bodden and Antonino Sabetta",

note = "Publisher Copyright: {\textcopyright} 2003-2012 IEEE.",

year = "2023",

month = apr,

doi = "10.1109/MSEC.2023.3236543",

language = "English",

volume = "21",

pages = "53--56",

journal = "IEEE Security and Privacy",

issn = "1540-7993",