Detection of Phishing Website Using Learning Techniques

Abstract

Phishing sites which expects to take the victims confidential data by diverting them to surf a fake website page that resembles a honest to goodness one is another type of criminal acts through the internet and its one of the especially concerns toward numerous areas including e-managing an account and retailing. Phishing site detection is truly an unpredictable and element issue including numerous components and criteria that are not stable. On account of the last and in addition ambiguities in arranging sites because of the intelligent procedures programmers are utilizing, some keen proactive strategies can be helpful and powerful tools can be utilized, for example, fuzzy, neural system and data mining methods can be a successful mechanism in distinguishing phishing sites. In Phishing E-mail Detection Based on Structural Properties, the proposed approach explains to find phishing through appropriate identification and usage of structural properties of email. The experiment is done by SVM and classification technique to classify phishing e-mails. The technique is used to identify phishing e- mails, which is low in efficiency and scalability. This is purely based on structural properties of e-mail and it has to extend more structural or content properties to reduce error results. Identifying phishing target based on semantic link network, the paper proposes a novel approach to discover phishing website by calculating association relation among webpages that include malicious webpages and its associated webpages to measure the combination of text relation, link relation and search relation. The semantic link network proposes a strategy based on situations to identify the suspicious webpage as phishing. The disadvantage in this approach is more kind of association has to be done, similarities between visual, layout and domain has to be related. This method is considered as a time consuming approach and also various sub-relations in the combined association relations are studied. Fuzzy Neural Network for Phishing Emails Detection deals with phishing email. It distinguishes phishing email and ham email in online mode. It is adopted on rank fetching, feature fetching and grouping similar features of email. The technique is based on binary value 0 or 1 to produce the result for all features used in this method, where 1 denotes a phishing feature and 0 for non-phishing. This technique does not have much dynamic system and thus it is inadequate in performance to produce accurate results. Intelligent Phishing