Catch'em all: Classification of Rare, Prominent, and Novel Malware Families

arXiv:2403.02546v1 Announce Type: new
Abstract: National security is threatened by malware, which remains one of the most dangerous and costly cyber threats. As of last year, researchers reported 1.3 billion known malware specimens, motivating the use of data-driven machine learning (ML) methods for analysis. However, shortcomings in existing ML approaches hinder their mass adoption. These challenges include detection of novel malware and the ability to perform malware classification in the face of class imbalance: a situation where malware families are …

analysis arxiv catch classification cs.cr cyber cyber threats data data-driven families machine machine learning malware national national security novel researchers security threats