Conference paper

MICHLOVSKÝ Zbyněk. String Kernel Based SVM for Internet Security Implementation. In: Neural Information Processing. Berlin / Heidelberg: Springer Verlag, 2009, pp. 530-539. ISBN 978-3-642-10682-8.
Publication language:english
Original title:String Kernel Based SVM for Internet Security Implementation
Title (cs):Aplikace SVM pro internetovou bezpečnost, založené na řetězcových jádrech
Pages:530-539
Proceedings:Neural Information Processing
Conference:ICONIP 2009 : 16th International Conference on Neural Information Processing
Series:Lecture Notes in Computer Science
Place:Berlin / Heidelberg, DE
Year:2009
ISBN:978-3-642-10682-8
Publisher:Springer Verlag
Keywords
SVM, string kernel functions, internet security
Annotation
In this work, we develop SVM based string kernel method according to different mathematical similarity expressions of two strings/substrings. For network security, we derive string kernel SVM for automatical attack (i.e. spam emails) signature analysis, conducting spam filtering without early determined spam signature. Moreover, we have used string kernel SVM to authenticate legitimate network applications.
Abstract
For network intrusion and virus detection, ordinary methods detect malicious network traffic and viruses by examining packets, flow logs or content of memory for any signatures of the attack. This implies that if no signature is known/created in advance, attack detection will be problematical. Addressing unknown attacks detection, we develop in this paper a network traffic and spam analyzer using a string kernel based SVM (support vector machine) supervised machine learning. The proposed method is capable of detecting network attack without known/earlier determined attack signatures, as SVM automatically learning attack signatures from traffic data. For application to internet security, we have implemented the proposed method for spam email detection over the SpamAssasin and E. M. Canada datasets, and network application authentication via real connection data analysis. The obtained above 99% accuracies have demonstrated the usefulness of string kernel SVMs on network security for either detecting 'abnormal' or protecting 'normal' traffic.
BibTeX:
@INPROCEEDINGS{
   author = {Zbyn{\v{e}}k Michlovsk{\'{y}}},
   title = {String Kernel Based SVM for Internet Security Implementation},
   pages = {530--539},
   booktitle = {Neural Information Processing},
   series = {Lecture Notes in Computer Science},
   year = {2009},
   location = {Berlin / Heidelberg, DE},
   publisher = {Springer Verlag},
   ISBN = {978-3-642-10682-8},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php.en.iso-8859-2?id=9135}
}

Your IPv4 address: 54.80.236.48
Switch to IPv6 connection

DNSSEC [dnssec]