Abstract | ||
---|---|---|
Automatic identification of anomalies on network data is a problem of fundamental interest to ISPs to diagnose in- cipient problems in their networks. ISPs gather diverse data sources from the network for monitoring, diagnos- tics or provisioning tasks. Finding anomalies in this data is a huge challenge due to the volume of the data col- lected, the number and diversity of data sources and the diversity of anomalies to be detected. In this paper we introduce a framework for anomaly detection that allows the construction of a black box anomaly detector. This anomaly detector can be used for automatically finding anomalies with minimal human in- tervention. Our framework also allows us to deal with the different types of data sources collected from the net- work. We have developed a prototype of this framework, TrafficComber, and we are in the process of evaluating it using the data in the warehouse of a tier-1 ISP. |
Year | Venue | Field |
---|---|---|
2006 | HotNets | Black box (phreaking),Data mining,Anomaly detection,Telecommunications,Computer science,Provisioning,Data type,Network data,Detector |
DocType | Citations | PageRank |
Conference | 3 | 0.67 |
References | Authors | |
17 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shobha Venkataraman | 1 | 1027 | 51.93 |
Juan Caballero | 2 | 1335 | 67.83 |
Dawn Song | 3 | 7334 | 385.37 |
Avrim Blum | 4 | 7978 | 906.15 |
Jennifer Yates | 5 | 790 | 64.51 |