Malware Analysis Datasets: PE Section Headers

Citation Author(s):
Submitted by:
Angelo Oliveira
Last updated:
Wed, 11/06/2019 - 06:10
Data Format:
0 ratings - Please login to submit your rating.


This dataset is part of my PhD research on malware detection and classification using Deep Learning. It contains static analysis data (PE Section Headers of the .text, .code and CODE sections) extracted from the 'pe_sections' elements of Cuckoo Sandbox reports. PE malware examples were downloaded from PE goodware examples were downloaded from and from Windows 7 x86 directories.



Column name: hash
Description: MD5 hash of the example
Type: 32 bytes string

Column name: size_of_data
Description: The size of the section on disk
Type: Integer

Column name: virtual_address
Description: Memory address of the first byte of the section relative to the image base
Type: Integer

Column name: entropy
Description: Calculated entropy of the section
Type: Float

Column name: virtual_size
Description: The size of the section when loaded into memory
Type: Integer

Column name: malware
Description: Class
Type: 0 (Goodware) or 1 (Malware)


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.


Please refer to the dataset DOI.
Please feel free to contact me for any further information.