BETH dataset: real cybersecurity data for anomaly detection research
Author(s)
Highnam, Kate
Arulkumaran, Kai
Hanif, Zachary
Jennings, Nicholas
Type
Working Paper
Abstract
We present the BETH cybersecurity dataset for anomaly detection and out-of-distribution analysis. With real “anomalies” collected using a novel tracking system, our dataset contains over eight million data points tracking 23 hosts. Each host has captured benign activity and, at most, a single attack, enabling cleaner behavioural analysis. In addition to being one of the most modern and extensive cybersecurity datasets available, BETH enables the development of anomaly detection algorithms on heterogeneously-structured real-world data, with clear downstream applications. We give details on the data collection, suggestions on pre-processing, and analysis with initial anomaly detection benchmarks on a subset of the data.
Date Issued
2021-07-23
Citation
2021
Publisher
Gatsby Computational Neuroscience Unit
Copyright Statement
© 2021 The Author(s).
Identifier
http://www.gatsby.ucl.ac.uk/~balaji/udl2021/accepted-papers/UDL2021-paper-033.pdf
Publication Status
Published