Random Projection and Multiscale Wavelet Leader Based Anomaly Detection and Address Identification in Internet Traffic

Abstract : We present a new anomaly detector for data traffic, `SMS', based on combining random projections (sketches) with multiscale analysis, which has low computational complexity. The sketches allow `normal' traffic to be automatically and robustly extracted, and anomalies detected, without the need for training data. The multiscale analysis extracts statistical descriptors, using wavelet leader tools developed recently for multifractal analysis, without any need for timescales to be selected a priori. The proposed detector is illustrated using a large recent dataset of Internet backbone traffic from the MAWI archive, and compared against existing detectors.
Complete list of metadatas

Cited literature [29 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01511891
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Friday, April 21, 2017 - 5:14:32 PM
Last modification on : Thursday, October 17, 2019 - 8:55:54 AM
Long-term archiving on : Saturday, July 22, 2017 - 2:23:04 PM

File

fontugne_17038.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01511891, version 1
  • OATAO : 17038

Citation

Romain Fontugne, Patrice Abry, Kentaro Fukuda, Pierre Borgnat, Johan Mazel, et al.. Random Projection and Multiscale Wavelet Leader Based Anomaly Detection and Address Identification in Internet Traffic. 40th IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2015), Apr 2015, Brisbane, Australia. pp. 1-5. ⟨hal-01511891⟩

Share

Metrics

Record views

181

Files downloads

187