BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Unsupervised Network Anomaly Detection
DTSTART:20130612T163000
DTEND:20130612T173000
DTSTAMP:20260407T175839Z
UID:4c7e8341e262bacf1583daf4a11bb562de332ab2bede348ae2279d6a
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr. Philippe Owezarski\, CNRS\, Toulouse\nNetwork anomaly dete
 ction is a critical aspect of network management for instance for QoS\, se
 curity\, etc. The continuous arising of new anomalies and attacks create a
  continuous challenge to cope with events that put the network integrity a
 t risk. Most network anomaly detection systems proposed so far employ a su
 pervised strategy to accomplish the task\, using either signature-based de
 tection methods or supervised-learning techniques. However\, both approach
 es present major limitations: the former fails to detect and characterize 
 unknown anomalies (letting the network unprotected for long periods)\, the
  latter requires training and labeled traffic\, which is difficult and exp
 ensive to produce. Such limitations impose a serious bottleneck to the pre
 viously presented problem. We introduce an unsupervised approach to detect
  and characterize network anomalies\, without relying on signatures\, stat
 istical training\, or labeled traffic\, which represents a significant ste
 p towards the autonomy of networks. Unsupervised detection is accomplished
  by means of robust data-clustering techniques\, combining Sub-Space clust
 ering with Evidence Accumulation or Inter-Clustering Results Association\,
  to blindly identify anomalies in traffic flows. Several post-processing t
 echniques such as correlation\, ranking and characterization\, are applied
  on extracted anomalies to improve results and reduce operator workload. T
 he detection and characterization performances of the unsupervised approac
 h are evaluated on real network traffic.
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CANCELLED
END:VEVENT
END:VCALENDAR