The evaluation of Network Anomaly Detection Systems: Statistical analysis of the UNSW-NB15 data set and the comparison with the KDD99 data set

By Nour Moustafa, Jill Slay. Information Security Journal, 2016

1,076 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A GA-LR wrapper approach for feature selection in network intrusion detection (2017, background): “This latter is considered as a new benchmark dataset that can be used for IDSs evaluation by the NIDS research community (Moustafa and Slay, 2016).”
Variational LSTM Enhanced Anomaly Detection for Industrial Big Data (2021, methodology): “UNSW-NB15 is generated by an Australian security laboratory using IXIA Per-fectStrom tool, which combines the real normal network trafﬁc and man-made attack trafﬁc in the modern network [26].”
Internet of Things Applications, Security Challenges, Attacks, Intrusion Detection, and Future Visions: A Systematic Review (2021, background): “The skewedness of KDD-99 and NSL-KDD is almost removed in UNSW-NB15 [79], [80], consisting of 49 features and 10 target classes, whereas KDD consists of 41 features and 5 target classes.”
TSE-IDS: A Two-Stage Classifier Ensemble for Intelligent Anomaly-Based Intrusion Detection System (2019, background): “, [17], [20], [51], which have used the same datasets are considered.”
Survey on SDN based network intrusion detection system using machine learning approaches (2018, methodology): “The ADFA-LD12 dataset is a worthy successor for the KDD dataset [56], and the UNSW-NB15 dataset [57] was also used for academic research purpose.”