Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Abstract : This paper presents current work for the detection of anomalies in Netflow records by leveraging a kernel function method. Netflow records are spatially aggregated over time, such that the designed kernel function can capture topological and quantitative changes in network traffic time series.
https://hal.inria.fr/hal-01529787 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Wednesday, May 31, 2017 - 1:17:49 PM Last modification on : Wednesday, May 31, 2017 - 1:19:35 PM Long-term archiving on: : Wednesday, September 6, 2017 - 4:06:02 PM
Cynthia Wagner, Thomas Engel. Detecting Anomalies in Netflow Record Time Series by Using a Kernel Function. 6th International Conference on Autonomous Infrastructure (AIMS), Jun 2012, Luxembourg, Luxembourg. pp.122-125, ⟨10.1007/978-3-642-30633-4_16⟩. ⟨hal-01529787⟩