Skip to main content

Datasets

Open Access

Malware Analysis Datasets: Raw PE as Image

Dataset image
Citation Author(s):
Angelo Oliveira
Submitted by:
Angelo Oliveira
Last updated:
DOI:
10.21227/8brp-j220
Data Format:
.csv
3438 views
Categories:
Keywords:
Machine Learning
malware
Detection
computer security
static analysis
No Ratings Yet
CITE SHARE/EMBED

Abstract

This dataset is part of my PhD research on malware detection and classification using Deep Learning. It contains static analysis data: Raw PE byte stream rescaled to a 32 x 32 greyscale image using the Nearest Neighbor Interpolation algorithm and then flattened to a 1024 bytes vector. PE malware examples were downloaded from virusshare.com. PE goodware examples were downloaded from portableapps.com and from Windows 7 x86 directories.

Instructions:

* FEATURES * Column name: hash Description: MD5 hash of the example Type: 32 bytes string Column name: pix_0 Description: The first greyscale pixel value Type: Integer (0-255) Column name: pix_1023 Description: The last greyscale pixel value Type: Integer (0-255) Column name: malware Description: Class Type: 0 (Goodware) or 1 (Malware) * ACKNOWLEDGMENTS * We would like to thank: Cuckoo Sandbox for developing such an amazing dynamic analysis environment! VirusShare! Because sharing is caring! Universidade Nove de Julho for supporting this research. Coordination for the Improvement of Higher Education Personnel (CAPES) for supporting this research. * CITATIONS * Please refer to the dataset DOI. Please feel free to contact me for any further information.

Dataset Files

LOGIN TO ACCESS DATASET FILES
Open Access dataset files are accessible to all logged in users. Don't have a login? Create a free IEEE account. IEEE Membership is not required.

QUESTIONS?