Net-GAN : Recurrent generative adversarial networks for network anomaly detection in multivariate time-series.
Resumen:
We introduce Net-GAN, a novel approach to network anomaly detection in time-series, using recurrent neural networks (RNNs) and generative adversarial learning (GAN). Different from the state of the art, which traditionally focuses on univariate measurements, Net-GAN detects anomalies in multivariate timeseries, exploiting temporal dependencies through RNNs. Net- GAN discovers the underlying distribution of the baseline, multivariate data, without making any assumptions on its nature, offering a powerful approach to detect anomalies in complex, difficult to model network monitoring data
| 2020 | |
|
Computing methodologies Anomaly detection Machine learning algorithms Multivariate time-series Generative models GAN LSTM |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
| https://hdl.handle.net/20.500.12008/25478 | |
| Acceso abierto | |
| Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0) |
| Sumario: | Transferencia tecnológica. Grupo de investigación Detección de anomalías en series de tiempo, Facultad de Ingeniería. Instituto de Ingeniería Eléctrica |
|---|
