Title: Malware classifier for dynamic deep learning algorithm

Authors: Young-bok Cho

Addresses: Department of Information Security, Daejeon University, 62, Daehak-ro, Dong-gu, Daejeon 34520, South Korea

Abstract: In this study, we propose a malware classification model that can handle length input data using the Microsoft Malware Classification Challenge dataset. The model is based on imaging existing data from malware. The proposed model generates a large number of images when malware data are large and generates a small image with small data. Dynamic RNN learns the generated image as time series data. The RNN output value is classified into malware by using only the highest weighted output by employing the attention technique and learning the RNN output value by residual CNN again. Experiments on the proposed model showed a micro-average F1 score of 92% in the validation dataset. Experimental results demonstrated that the performance of a model capable of learning and classifying arbitrary length data can be verified without special feature extraction and dimension reduction.

Keywords: convolution neural network; malware; deep learning; recurrent neural network; Kaggle data.

DOI: 10.1504/IJCVR.2021.117577

International Journal of Computational Vision and Robotics, 2021 Vol.11 No.5, pp.486 - 496

Received: 09 Nov 2019
Accepted: 04 Apr 2020

Published online: 19 Aug 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article