"Malicious Document Detection Dataset 2025"
Abstract
"This repository provides EMBER-like metadata exports and pre-computed basic statistics for document malware detection experiments across PDF and Office formats. The core design goal is to make the dataset reproducible and easy to consume in pipelines that follow the EMBER2024-style JSONL format, while keeping the train\/test split and per-file identifiers explicit. "
Fields of Study & Subjects
Advanced Malware Detection Techniques
Spam and Phishing Detection
Adversarial Robustness in Machine Learning
Publication details
- Journal / source
- IEEE DataPort
- Publication date
- 11 February 2026
- Language
- EN
- Document type
- Dataset