DECISION MODEL ANALYSIS FOR SPAM

Abstract

One of the security challenges in e-Government is to offer a smooth dialogue with citizens, which guarantees the availability, confidentiality and integ- rity of the information interchanged. Spam jeopardizes the survival of electronic mail as a communication means. Many approaches to tackle the problem with spam have been proposed. This paper shows the necessity of studying the real value of spam filters. Contrary to common belief, false positive rate and false negative rate do not completely reveal to what extent a junk filter is worth using. Very important parameters like the hostility of the environment (summarized by the probability of receiving spam) or the error costs associated with the filter play a decisive role.