MAWILab: combining diverse anomaly detectors for automated anomaly labeling and performance benchmarking

By Romain Fontugne, Pierre Borgnat, Patrice Abry, Kensuke Fukuda. Conference on Emerging Network Experiment and Technology, 2010

359 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.

Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications (2018, background): “Simple ensemble of these detectors, such as majority vote [8] and normalization [32], do not help much either according to [23].”
Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study (2020, methodology): “For more details about the MAWI dataset, we refer the reader to the work presented by Fontugne et al. [93].”
A Survey of Network-based Intrusion Detection Data Sets (2019, methodology): “MAWI [64].”
Anomaly Detection in Streams with Extreme Value Theory (2017, methodology): “In these captures, MAWIlab [19] finds anomalies and labels them with the taxonomy proposed by Mazel et al.”
Deep Learning for Anomaly Detection: A Survey (2019, background): “Fraud is a deliberate act of deception to access valuable resources (Abdallah et al. [2016]).”
Event labeling combining ensemble detectors and background knowledge (2014, background): “The benefit of combining different detectors relies on diversity among detectors ensembles [20].”