Published September 28, 2019 | Version v1

Detection of malicious PDF files using a two-stage machine learning algorithm

Authors/Creators

  • 1. State Key Laboratory of Mathematical Engineering and Advanced Computing

Description

MALWARE_PDF_PRE_04-2011.zip  is a dataset that contains malicious PDF samples obtained from VirusTotal by April 2011. 

2017-12-05-PDF.7z is a dataset that contains malicious PDF samples obtained from VirusTotal by May 2017. 

CLEAN_PDF_9000_files.zip  is a dataset that contains 9000 benign PDF files obtained from various open sources, and they are all labeled benign by antivirus systems. 

Files

CLEAN_PDF_9000_files.zip

Files (1.1 GB)

Name Size
md5:cc17a2fa1d8c765f6e0cf1791560da57
258.0 MB Download
md5:1fee26f6ef5d01816a13164bfc8a7d27
683.3 MB Preview Download
md5:9d041932d13f4ef494d9ac9768f363f2
129.1 MB Preview Download