ORBi: Jung Tobias - Contextual Multi-armed Bandits for Web Server Defense

Reference : Contextual Multi-armed Bandits for Web Server Defense


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/115630

Title :	Contextual Multi-armed Bandits for Web Server Defense
Language :	English
Author, co-author :	Jung, Tobias [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
	Martin, Sylvain [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
	Ernst, Damien [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
	Leduc, Guy [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
Publication date :	2012
Main document title :	Proceedings of 2012 International Joint Conference on Neural Networks (IJCNN)
Editor :	Hussein, Abbas
Publisher :	IEEE
Pages :	8
Peer reviewed :	Yes
On invitation :	No
Audience :	International
ISBN :	978-1-4673-1488-6
Event name :	2012 International Joint Conference on Neural Networks (IJCNN)
Event date :	from 10-6-2012 to 15-6-2012
Event organizer :	IEEE
Event place (city) :	Brisbane
Event country :	Australia
Keywords :	[en] reinforcement learning ; contextual bandits ; web server
Abstract :	[en] In this paper we argue that contextual multi-armed bandit algorithms could open avenues for designing self-learning security modules for computer networks and related tasks. The paper has two contributions: a conceptual and an algorithmical one. The conceptual contribution is to formulate the real-world problem of preventing HTTP-based attacks on web servers as a one-shot sequential learning problem, namely as a contextual multi-armed bandit. Our second contribution is to present CMABFAS, a new algorithm for general contextual multi-armed bandit learning that specifically targets domains with finite actions. We illustrate how CMABFAS could be used to design a fully self-learning meta filter for web servers that does not rely on feedback from the end-user (i.e., does not require labeled data) and report first convincing simulation results.
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Target :	Researchers
Permalink :	http://hdl.handle.net/2268/115630
DOI :	10.1109/IJCNN.2012.6252760
Other URL :	http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6241467
Framework Programme / European Project :	FP7 ; 224619 - RESUMENET - Resilience and Survivability for future networking: framework, mechanisms, and experimental evaluation

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	main_cr.pdf	(svn r214)	Author preprint	335.05 kB	View/Open

Additional material(s):

	File	Commentary	Version	Size	Access
Open access	IJCNN2012_slides.pdf	Slides from talk	-	770.35 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5