MH-1M: A 1.34 Million-Sample Multi-Feature Android Malware Dataset with Rich Metadata
Hendrio Bragança, Diego Kreutz, Vanderson Rocha, Joner Assolin, Eduardo Feitosa · 2025
Read MH-1M: A 1.34 Million-Sample Multi-Feature Android Malware Dataset with Rich Metadata by Hendrio Bragança, Diego Kreutz, Vanderson Rocha, Joner Assolin, Eduardo Feitosa (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12873278.txt.
Description
Hendrio Bragança and co-authors released MH-1M in 2025, a large dataset for Android malware research. The set holds over 1.34 million applications with rich features and metadata. Labels come from the VirusTotal service, which combines many detection engines for a reliable verdict on each app. The data is openly shared through several public repositories.
The full release passes four hundred gigabytes. It includes the outputs of the feature extraction pipeline and the VirusTotal report for each sample. The authors built the set to track how Android malware keeps changing. Older datasets age fast as attackers shift tactics, so fresh, large collections matter for training detectors. MH-1M is offered as shared ground for that work, letting teams compare methods on the same million-scale sample.
Catalog record
| CREATOR | Hendrio Bragança, Diego Kreutz, Vanderson Rocha, Joner Assolin, Eduardo Feitosa |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 62 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |