Multi-feature Dataset for Windows PE Malware Classification

TL;DR

This paper introduces a comprehensive multi-feature dataset of Windows PE malware samples, enabling improved static analysis and machine learning-based detection of malicious executables.

Contribution

It provides a publicly available, multi-feature dataset of Windows PE malware samples with detailed feature sets for research and development in malware detection.

Findings

Dataset includes 18,551 samples across five malware families.

Features encompass DLLs, functions, PE header, and section data.

Dataset aims to facilitate machine learning research in static malware analysis.

Abstract

This paper describes a multi-feature dataset for training machine learning classifiers for detecting malicious Windows Portable Executable (PE) files. The dataset includes four feature sets from 18,551 binary samples belonging to five malware families including Spyware, Ransomware, Downloader, Backdoor and Generic Malware. The feature sets include the list of DLLs and their functions, values of different fields of PE Header and Sections. First, we explain the data collection and creation phase and then we explain how did we label the samples in it using VirusTotal's services. Finally, we explore the dataset to describe how this dataset can benefit the researchers for static malware analysis. The dataset is made public in the hope that it will help inspire machine learning research for malware detection.