Likelihood ratios and recurrent random neural networks in detection of denial of service attacks
Loukas, George ORCID: 0000-0003-3559-5182 and Oke, Gulay
(2007)
Likelihood ratios and recurrent random neural networks in detection of denial of service attacks.
In: 2007 International Symposium on Performance Evaluation of Computer and Telecommunication Systems, 16-18 July 2007, San Diego, CA, USA.
|
PDF (Author's Accepted Manuscript)
15024_Loukas_Likelihood ratios and recurrent random (conf. paper) 2007.pdf - Accepted Version Download (254kB) | Preview |
Abstract
In a world that is becoming increasingly dependent on In- ternet communication, Denial of Service (DoS) attacks have evolved into a major security threat which is easy to launch but difficult to defend against. In order for DoS countermea- sures to be effective, the attack must be detected early and accurately. In this paper we propose a DoS detection tech- nique based on observation of the incoming traffic and a com- bination of traditional likelihood estimation with a recurrent random neural network (r-RNN) structure. We select input features that describe essential information on the incoming traffic and evaluate the likelihood ratios for each input, to fuse them with a r-RNN. We evaluate the performance of our method in terms of false alarm and correct detection rates with experiments on a large networking testbed, for a variety of input traffic.
Item Type: | Conference or Conference Paper (Paper) |
---|---|
Uncontrolled Keywords: | denial of service, network security, intrusion detection |
Faculty / School / Research Centre / Research Group: | Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS) |
Related URLs: | |
Last Modified: | 26 Nov 2020 22:35 |
URI: | http://gala.gre.ac.uk/id/eprint/15024 |
Actions (login required)
![]() |
View Item |
Downloads
Downloads per month over past year