UGR'16: A new dataset for the evaluation of cyclostationarity-based network IDSs. Issue 73 (March 2018)

• Record Type: Journal Article
• Authors: Maciá-Fernández, Gabriel; Camacho, José; Magán-Carrión, Roberto; García-Teodoro, Pedro; Therón, Roberto
• Is Part Of: Computers & security. Issue 73(2018)
• Page Start: 411
• Page End: 424
• Publication Date: 2018-03
• Subjects: Network security -- Dataset -- IDS -- Network traffic -- Netflow; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2017.11.004
• Languages: English
• ISSNs: 0167-4048

Abstract

Abstract: The evaluation of algorithms and techniques to implement intrusion detection systems heavily rely on the existence of well designed datasets. In the last years, a lot of efforts have been done toward building these datasets. Yet, there is still room to improve. In this paper, a comprehensive review of existing datasets is first done, making emphasis on their main shortcomings. Then, we present a new dataset that is built with real traffic and up-to-date attacks. The main advantage of this dataset over previous ones is its usefulness for evaluating IDSs that consider long-term evolution and traffic periodicity. Models that consider differences in daytime/nighttime or weekdays/weekends can also be trained and evaluated with it. We discuss all the requirements for a modern IDS evaluation dataset and analyze how the one presented here meets the different needs.