Datasets:
EMBER (https://github.com/elastic/ember):
Anderson, H.S., Roth, P.: EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models, http://arxiv.org/abs/1804.04637, (2018)
SOREL-20M (https://github.com/sophos/SOREL-20M):
Harang, R., Rudd, E.M.: SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection, http://arxiv.org/abs/2012.07634, (2020)
Model adapted from:
Ethan M Rudd, Felipe N Ducau, Cody Wild, Konstantin Berlin, and Richard Harang. Aloha: Auxiliary loss optimization for hypothesis augmentation. In 28th {USENIX} Security Symposium ({USENIX} Security 19), pages 303–320, 2019.