Towards Systematic Traffic Annotation

Abstract : Maintaining Internet network resources available and se- cured is an unmet challenge. Hence, tracffic classication and anomaly detection received much attention in the last few years, and several algorithms have been proposed for backbone traces. However, the evaluation of these methods usually lacks rigor, leading to hasty conclusions. A systematic approach permits to maintain updated database in which recent traces are regularly added, and labels are improved with upcoming algorithms. In this paper we discuss the difficulties faced in comparing events provided by distinct algorithms, and propose a methodology to achieve it.
Type de document :
Communication dans un congrès
CoNEXT'09 Student Workshop, Dec 2009, Roma, Italy. ACM, 2009
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger
Contributeur : Pierre Borgnat <>
Soumis le : vendredi 23 avril 2010 - 13:23:57
Dernière modification le : jeudi 19 avril 2018 - 14:54:03
Document(s) archivé(s) le : lundi 22 octobre 2012 - 15:22:14


Fichiers produits par l'(les) auteur(s)


  • HAL Id : ensl-00475933, version 1



Romain Fontugne, Pierre Borgnat, Patrice Abry, Kensuke Fukuda. Towards Systematic Traffic Annotation. CoNEXT'09 Student Workshop, Dec 2009, Roma, Italy. ACM, 2009. 〈ensl-00475933〉



Consultations de la notice


Téléchargements de fichiers