An Innovative Analyser for Email Classification Based on Grey List Analysis

Abstract

In this paper we propose a new technique of email classification based on grey list (GL) analysis of user emails. This technique is based on the analysis of output emails of an integrated model which uses multiple classifiers of statistical learning algorithms [8]. The GL is a list of classifier/(s) output which is/are not considered as true positive (TP) and true negative (TN) but in the middle of them. Many works have been done to filter spam from legitimate emails using classification algorithm and substantial performance has been achieved with some amount of false positive (FP) tradeoffs. In the case of spam detection the FP problem is unacceptable, sometimes. The proposed technique will provide a list of output emails, called "grey list (GL)", to the analyser for making decisions about the status of these emails. It has been shown that the performance of our proposed technique for email classification is much better compare to existing systems, in order to reducing FP problems and accuracy.

Spam filtering for network traffic security on a multi‐core environment

“…The spam filter architecture was originally designed and developed for a single SVM classifier as detailed in [3,4]. We extended this architecture to be used for an ensemble-based generic multi-classifier that processes the information in serial [5].…”

Multi-classifier Classification of Spam Email on a Ubiquitous Multi-core Architecture

“…The spam filter architecture was originally designed and developed for a single SVM classifier as detailed in [15,14]. We extended this architecture to be used for an ensemble based generic multiclassifier that processes the information in serial [13].…”

“…While previous research in spam classification is primarily concerned with using a text based single classifier [15,14] to detect spam messages, we have developed a novel spam filter architecture using a multi-classifier approach [13].…”

A multi-tier phishing detection and filtering approach

“…Different phishing corpuses have been used in our experiments and an analyzation has been made with regards to data set construction, evaluation metrics and preliminary setup. It has been shown that the performance of ML algorithm varies from one another even for same corpora (Islam et al, 2009). Based on this idea, we have experimented the rescheduling of the ML algorithms among the tiers and found variation of result.…”

“…The Internet services are used daily by millions of people to communicate around the globe and are a mission-critical application for many businesses (Islam et al, 2009). However, phishing has become one of the biggest worldwide problems facing the Internet users today over the last decade (Phishing activity trends report, 2005).…”