{"url":"/dataset/bodmas","name":"BODMAS","full_name":"Blue Hexagon Open Dataset for Malware AnalysiS","description_markdown":"We collaborate with Blue Hexagon to release a dataset containing timestamped malware samples and well-curated family information for research purposes. \r\nThe BODMAS dataset contains 57,293 malware samples and 77,142 benign samples collected from August 2019 to September 2020,  with carefully curated family information (581 families).\r\nWe also provide preprocessed feature vectors and metadata available to everyone.\r\nThe malware binaries can be obtained per request.\r\n\r\nSource: [BODMAS: An Open Dataset for Learning based Temporal Analysis of PE Malware](https://liminyang.web.illinois.edu/data/DLS21_BODMAS.pdf)","description_withheld":null,"homepage":"https://whyisyoung.github.io/BODMAS/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Malware Classification","url":"/task/malware-classification","datasets_with_task":"/datasets/task/malware-classification"},{"name":"Malware Detection","url":"/task/malware-detection","datasets_with_task":"/datasets/task/malware-detection"},{"name":"Malware Clustering","url":"/task/malware-clustering","datasets_with_task":"/datasets/task/malware-clustering"},{"name":"Behavioral Malware Classification","url":"/task/behavioral-malware-classification","datasets_with_task":"/datasets/task/behavioral-malware-classification"},{"name":"Behavioral Malware Detection","url":"/task/behavioral-malware-detection","datasets_with_task":"/datasets/task/behavioral-malware-detection"},{"name":"Malware Analysis","url":"/task/malware-analysis","datasets_with_task":"/datasets/task/malware-analysis"}],"languages":[],"variants":["BODMAS"],"data_loaders":[{"repo":"https://github.com/whyisyoung/BODMAS","url":"https://whyisyoung.github.io/BODMAS/","frameworks":["tf","pytorch"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}