Synthetic dataset generator for anomaly detection in a university environment

Article type: Research Article

Authors: Strnad, Pavel | Švarc, Lukáš | Berka, Petr

Affiliations: Department of Information and Knowledge Engineering, Prague University of Economics and Business, Prague, Czech Republic

Correspondence: [*] Corresponding author: Pavel Strnad, Department of Information and Knowledge Engineering, Prague University of Economics and Business, W. Churchill Sq. 1938/4, 130 67 Prague 3 Žižkov, Czech Republic. Tel.: +420 731 135 806; E-mail: pavel.strnad@vse.cz.

Abstract: This article introduces a recently developed synthetic dataset generator, which contains anonymised data from the Prague University of Economics and Business information system logs. The generator is opensource and is able to scale this data time-wise and also perform injection of the data with cyberattackers’ behaviour patterns. The anonymised data still contains user behaviour patterns; therefore, individual anomalous behaviour can be detected. Different types of real attack behaviour patterns in the university environment have been selected; they are used to demonstrate attackers’ behaviour in synthetically created system logs. The mentioned features allow other researchers to benchmark their anomaly detection algorithms with complex data.

Keywords: Anomaly detection, automated attacks, dataset, machine learning, synthetic generator, university environment

DOI: 10.3233/IDA-216511

Journal: Intelligent Data Analysis, vol. 27, no. 2, pp. 417-422, 2023