Multi-Layer Perceptron Backpropagation for Enhanced Detection of Spam Mails

Abstract

In today’s technological world everything is done online, for communicating with the business
partner, students, friends, etc. we used email application, which easily share files information to
another user. The general problem for all the users which are used email application for
communication is phishing. It is one of the types of cyber-attack in which fradaunt used the fake
message and fake sites for trapping money from clients. Attackers attempt to draw online clients by
persuading them to share their username, passwords, bank account information for fill billing data.
One of the principle issues of phishing email location is the unknown "zero-day" phishing attack,
which builds the level of trouble to recognize phishing email. These days, phishers are making diverse
portrayal strategies to make unknown "zero-day" phishing email to break the barriers of those
locators. There are number of techniques are developed for phishing detection, but these systems were
fail to provide appropriate results. In this paper we proposed the technique for detecting the phishing
mails by using multi-layer perceptron classifier. System can check the mail in the blacklist mail ids
first, it email-id exist their then it can store directly, if not exist system perform the classification
algorithm and detect the mail is real mail or phishing mail. System is compared with the existing
system used for phishing detection.