Reference : Contextual Multi-armed Bandits for Web Server Defense
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/115630
Contextual Multi-armed Bandits for Web Server Defense
English
Jung, Tobias mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
Martin, Sylvain mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
Ernst, Damien mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Leduc, Guy mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
2012
Proceedings of 2012 International Joint Conference on Neural Networks (IJCNN)
Hussein, Abbas
IEEE
8
Yes
No
International
978-1-4673-1488-6
2012 International Joint Conference on Neural Networks (IJCNN)
from 10-6-2012 to 15-6-2012
IEEE
Brisbane
Australia
[en] reinforcement learning ; contextual bandits ; web server
[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.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Researchers
http://hdl.handle.net/2268/115630
10.1109/IJCNN.2012.6252760
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6241467
FP7 ; 224619 - RESUMENET - Resilience and Survivability for future networking: framework, mechanisms, and experimental evaluation

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
main_cr.pdf(svn r214)Author preprint335.05 kBView/Open

Additional material(s):

File Commentary Size Access
Open access
IJCNN2012_slides.pdfSlides from talk770.35 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.