Publications

Automatic Discovery of Network Applications: A Hybrid Approach

Mahbod Tavallaee and Wei Lu and Ebrahim Bagheri and Ali A. Ghorbani
Reference:
Mahbod Tavallaee; Wei Lu; Ebrahim Bagheri and Ali A. Ghorbani Automatic Discovery of Network Applications: A Hybrid Approach. In Canadian Conference on AI, pages 208-219, 2010.
Links to Publication: [doi]
Abstract:
Automatic discovery of network applications is a very challenging task which has received a lot of attentions due to its importance in many areas such as network security, QoS provisioning, and network management. In this paper, we propose an online hybrid mechanism for the classification of network flows, in which we employ a signature-based classifier in the first level, and then using the weighted unigram model we improve the performance of the system by labeling the unknown portion. Our evaluation on two real networks shows between 5% and 9% performance improvement applying the genetic algorithm based scheme to find the appropriate weights for the unigram model.
Bibtex Entry:
@inproceedings{DBLP:conf/ai/TavallaeeLBG10, author = {Mahbod Tavallaee and Wei Lu and Ebrahim Bagheri and Ali A. Ghorbani}, title = {Automatic Discovery of Network Applications: A Hybrid Approach}, booktitle = {Canadian Conference on AI}, year = {2010}, pages = {208-219}, ee = {http://dx.doi.org/10.1007/978-3-642-13059-5_21}, crossref = {DBLP:conf/ai/2010}, bibsource = {DBLP, http://dblp.uni-trier.de}, abstract = { Automatic discovery of network applications is a very challenging task which has received a lot of attentions due to its importance in many areas such as network security, QoS provisioning, and network management. In this paper, we propose an online hybrid mechanism for the classification of network flows, in which we employ a signature-based classifier in the first level, and then using the weighted unigram model we improve the performance of the system by labeling the unknown portion. Our evaluation on two real networks shows between 5% and 9% performance improvement applying the genetic algorithm based scheme to find the appropriate weights for the unigram model. } }




Powered by WordPress