Improving Classification of Metamorphic Malware by Augmenting Training Data with a Diverse Set of Evolved Mutant Samples

Babaagba, Kehinde; Tan, Zhiyuan; Hart, Emma

Abstract

Detecting metamorphic malware provides a challenge to machine-learning models as trained models might not generalise to future mutant variants of the malware. To address this, we explore whether machine-learning models can be improved by augmenting training data-sets with samples of potential variants. These variants are generated using an evolutionary algorithm that evolves a behaviourally diverse set of mutants, optimised to avoid detection by a large set of existing detection-engines. Using features calculated from the behavioural trace of a sample as input, we evaluate the ability of five machine-learning methods to detect the new variants, show that the detection rate is considerably improved by including the new samples as training data, and that the classifiers still generalise over a range of malware. We then repeat this experiment using a sequence-based deep-learning method as the classifier, which is shown to out-perform the feature-based classifiers.

Citation

Babaagba, K., Tan, Z., & Hart, E. (2020). Improving Classification of Metamorphic Malware by Augmenting Training Data with a Diverse Set of Evolved Mutant Samples. . https://doi.org/10.1109/CEC48606.2020.9185668

• Conference Name: The 2020 IEEE Congress on Evolutionary Computation (IEEE CEC 2020)
• Conference Location: Glasgow, UK
• Start Date: Jul 19, 2020
• End Date: Jul 24, 2020
• Acceptance Date: Mar 20, 2020
• Online Publication Date: Sep 3, 2020
• Publication Date: Sep 3, 2020
• Deposit Date: Apr 28, 2020
• Publicly Available Date: Sep 3, 2020
• Publisher: Institute of Electrical and Electronics Engineers
• DOI: https://doi.org/10.1109/CEC48606.2020.9185668
• Keywords: Machine-learning; Evolutionary computing; Malware and Computer security
• Public URL: http://researchrepository.napier.ac.uk/Output/2656040