Reference : Contextual Multi-armed Bandits for the Prevention of Spam in VoIP Networks
E-prints/Working papers : First made available on ORBi
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/115524
Contextual Multi-armed Bandits for the Prevention of Spam in VoIP Networks
English
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 mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Réseaux informatiques >]
Jul-2012
arXiv 1201.6181
No
[en] Learning ; Bandits ; Networking
[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 one and an algorithmical one. The conceptual contribution is to formulate -- as an example -- the real-world problem of preventing SPIT (Spam in VoIP networks), which is currently not satisfyingly addressed by standard techniques, as a 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 SPIT filter that does not rely on feedback from the end-user (i.e., does not require labeled data) and report first simulation results.
Researchers
http://hdl.handle.net/2268/115524
Technical report.

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
TJ - arXiv 1201.6181.pdfAuthor postprint475.34 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.