{"url":"/dataset/ember","name":"EMBER","full_name":null,"description_markdown":"A labeled benchmark dataset for training machine learning models to statically detect malicious Windows portable executable files. The dataset includes features extracted from 1.1M binary files: 900K training samples (300K malicious, 300K benign, 300K unlabeled) and 200K test samples (100K malicious, 100K benign).\r\n\r\nSource: [EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models](https://arxiv.org/pdf/1804.04637v2.pdf)","description_withheld":null,"homepage":"https://github.com/endgameinc/ember","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ember-an-open-dataset-for-training-static-pe","title":"EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models","first_author":null,"url":null},"license":{"name":"MIT","url":"https://github.com/elastic/ember/blob/master/LICENSE.txt"},"modalities":[],"tasks":[{"name":"Feature Engineering","url":"/task/feature-engineering","datasets_with_task":"/datasets/task/feature-engineering"},{"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"}],"languages":[],"variants":["EMBER"],"data_loaders":[{"repo":"https://github.com/endgameinc/ember","url":"https://github.com/endgameinc/ember","frameworks":[]}],"num_papers_in_archive":115,"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."}