{"url":"/dataset/vnat","name":"VNAT","full_name":"VPN/NONVPN NETWORK APPLICATION TRAFFIC DATASET","description_markdown":"This dataset is a collection of labelled PCAP files, both encrypted and unencrypted, across 10 applications, as well as a pandas dataframe in HDF5 format containing detailed metadata summarizing the connections from those files. It was created to assist the development of machine learning tools that would allow operators to see the traffic categories of both encrypted and unencrypted traffic flows. In particular, features of the network packet traffic timing and size information (both inside of and outside of the VPN) can be leveraged to predict the application category that generated the traffic.","description_withheld":null,"homepage":"https://www.ll.mit.edu/r-d/datasets/vpnnonvpn-network-application-traffic-dataset-vnat","introduced_date":"2022-05-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/extensible-machine-learning-for-encrypted","title":"Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification","first_author":"Steven Jorgensen","url":null},"license":null,"modalities":[{"name":"Time series","url":"/datasets/modality/time-series"},{"name":"Tables","url":"/datasets/modality/tables"}],"tasks":[{"name":"Classification","url":"/task/classification-1","datasets_with_task":"/datasets/task/classification-1"},{"name":"Security Studies","url":"/task/security-studies","datasets_with_task":"/datasets/task/security-studies"}],"languages":[],"variants":["VNAT"],"data_loaders":[],"num_papers_in_archive":5,"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."}