Date of Publication :11th April 2017

Abstract: Pattern classification is a branch of machine learning that focuses on recognition of patterns and regularities in data. In adversarial applications like biometric authentication, spam filtering, network intrusion detection the pattern classification systems are used. Extending pattern classification theory and design methods to adversarial environment is thus a novel and very relevant research direction. Spam filtering to discriminate between a “legitimate” and a “malicious” pattern class. Intrusion analysis is the process of combing through IDS alerts and audit logs to identify real successful and attempted attacks. Phishing is a social engineering attack that exploits user’s ignorance during system processing has an impact on commercial and banking sectors. Numerous techniques are developed in the last years to detect phishing attacks such as authentication, security toolbars, blacklists, phishing emails, phishing websites, and URL analysis, In this paper, present phishing detection system using features extracted from URLs lexical only to meet two important goals which are wide scope of protection and applicability in a real-time system and calculate the probability of characters sequence in URLs using the N-gram model.

Reference :