Title :
A Prior Distribution for Anti-spam Statistical Bayesian Model
Author :
Begriche, Youcef ; Labiod, Houda
Author_Institution :
IEEE, Paris, France
Abstract :
This paper deals with Bayesian models applied to anti-spam. In most anti-spam related researches, authors assume that the probability of spam message is equal to 0.5, which is unrealistic. This pushes us to define a prior and a posterior probability laws to enhance the spam detection and increase the reliability decision. This work differs from previous results using the Bayesian approach for the anti-spam issue, especially through refinement and enhancement of various probability laws.
Keywords :
Bayes methods; unsolicited e-mail; anti-spam statistical Bayesian model; posterior probability laws; prior distribution; spam detection; spam message; Bayesian methods; Costs; Filtering; IEEE members; Information security; Information systems; Niobium; Probability; Telecommunications; Unsolicited electronic mail;
Conference_Titel :
Network and Service Security, 2009. N2S '09. International Conference on
Conference_Location :
Paris
Print_ISBN :
978-2-9532-4431-1
