Random Forest of Tensors (RFoT)

Abstract

Machine learning has become an invaluable tool in the fight against malware. Traditional supervised and unsupervised methods are not designed to capture the multidimensional details that are often present in cyber data. In contrast, tensor factorization is a powerful unsupervised data analysis method for extracting the latent patterns that are hidden in a multi-dimensional corpus. In this poster we explore the application of tensors to classification, and we describe a hybrid model that leverages the strength of multi-dimensional analysis combined with clustering. We introduce a novel semisupervised ensemble classifier named Random Forest of Tensors (RFoT) that is based on generating a forest of tensors in parallel, which share the same first dimension, and randomly selecting the remainder of the dimensions and entries of each tensor from the features set