Improving Malware Detection Accuracy by Extracting Icon Information
Authors:
- Pedro SilvaPSPedro Silva
- Sepehr Akhavan-MasoulehSASepehr Akhavan-Masouleh
- Li LiLLLi Li
- 1 April 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 408-411
Abstract
Detecting PE malware files is now commonly approached using statistical and machine learning models. While these models commonly use features extracted from the structure of PE files, we propose that icons from these files can also help better predict malware. We propose a new machine learning approach to extract information from icons. Our proposed approach consists of two steps: 1) extracting icon features using summary statics, a histogram of gradients (HOG), and a convolutional autoencoder, 2) clustering icons based on the extracted icon features. Using publicly available data and by using machine learning experiments, we show our proposed icon clusters significantly boost the efficacy of malware prediction models. In particular, our experiments show an average accuracy increase of 10 percent when icon clusters are used in the prediction model.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- On the nature and correction of the spurious S-wise spiral galaxy winding bias in Galaxy Zoo 1Monthly Notices of the Royal Astronomical Society, 2016
- Pure density functional for strong correlation and the thermodynamic limit from machine learningPhysical Review B, 2016
- ChaLearn LAP 2016: First Round Challenge on First Impressions - Dataset and Results2016
- Deep Residual Learning for Image Recognition2016
- Learning-Based and Data-Driven TCP Design for Memory-Constrained IoT2016
- Face recognition based on subset selection via metric learning on manifoldFrontiers of Information Technology & Electronic Engineering, 2015
- scikit-image: image processing in PythonPeerJ, 2014
- Learning Deep Architectures for AIFoundations and Trends in Machine Learning, 2009