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 | |
Publication status | Published - Apr 2023 |
Bibliographical note
Publisher Copyright:© 2003-2012 IEEE.