{"url":"/dataset/sorel-20m","name":"SOREL-20M","full_name":"Sophos/ReversingLabs-20 Million","description_markdown":"SOREL-20M is a large-scale dataset consisting of nearly 20 million files with pre-extracted features and metadata, high-quality labels derived from multiple sources, information about vendor detections of the malware samples at the time of collection, and additional “tags” related to each malware sample to serve as additional targets.\r\n\r\nSource: [SOREL-20M](https://github.com/sophos-ai/SOREL-20M)","description_withheld":null,"homepage":"https://github.com/sophos-ai/SOREL-20M","introduced_date":"2020-12-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/sorel-20m-a-large-scale-benchmark-dataset-for","title":"SOREL-20M: A Large Scale Benchmark Dataset for Malicious PE Detection","first_author":null,"url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["SOREL-20M"],"data_loaders":[{"repo":"https://github.com/sophos-ai/SOREL-20M","url":"https://github.com/sophos-ai/SOREL-20M","frameworks":["pytorch"]}],"num_papers_in_archive":14,"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."}