TY - GEN
T1 - Inferring applications at the network layer using collective traffic statistics
AU - Jin, Yu
AU - Duffield, Nick
AU - Haffner, Patrick
AU - Sen, Subhabrata
AU - Zhang, Zhi-Li
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - In this paper, we propose a novel technique for inferring the distribution of application classes present in the aggregated traffic flows between endpoints, which exploits both the statistics of the traffic flows, and the spatial distribution of those flows across the network. Our method employs a two-step supervised model, where the boot-strapping step provides initial (inaccurate) inference on the traffic application classes, and the graph-based calibration step adjusts the initial inference through the collective spatial traffic distribution. In evaluations using real traffic flow measurements from a large ISP, we show how our method can accurately classify application types within aggregate traffic between endpoints, even without the knowledge of ports and other traffic features. While the bootstrap estimate classifies the aggregates with 80% accuracy, incorporating spatial distributions through calibration increases the accuracy to 92%, i.e., roughly halving the number of errors.
AB - In this paper, we propose a novel technique for inferring the distribution of application classes present in the aggregated traffic flows between endpoints, which exploits both the statistics of the traffic flows, and the spatial distribution of those flows across the network. Our method employs a two-step supervised model, where the boot-strapping step provides initial (inaccurate) inference on the traffic application classes, and the graph-based calibration step adjusts the initial inference through the collective spatial traffic distribution. In evaluations using real traffic flow measurements from a large ISP, we show how our method can accurately classify application types within aggregate traffic between endpoints, even without the knowledge of ports and other traffic features. While the bootstrap estimate classifies the aggregates with 80% accuracy, incorporating spatial distributions through calibration increases the accuracy to 92%, i.e., roughly halving the number of errors.
KW - Design
KW - Measurement
UR - http://www.scopus.com/inward/record.url?scp=77954891495&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77954891495&partnerID=8YFLogxK
U2 - 10.1145/1811099.1811082
DO - 10.1145/1811099.1811082
M3 - Conference contribution
AN - SCOPUS:77954891495
SN - 9781450302111
T3 - Performance Evaluation Review
SP - 351
EP - 352
BT - SIGMETRICS'10 - Proceedings of the 2010 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems
T2 - 2010 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, SIGMETRICS'10
Y2 - 14 June 2010 through 18 June 2010
ER -