Machine Learning Approach to Efficient Phishing Detection

Phishing is a kind of cyber-attack in which perpetrators use spoofed emails and fraudulent web-sites to allure unsuspecting online users into giving up personal information. This project views phishing problem holistically by examining various research works and their countermeasures, and how to increase detection. It composes of studies which focus on dataset gathering, pre-processing, features extraction and dataset division in order to make the dataset suitable for the classification process. Phishing creates high rates of damage to internet user. The proposed system introduces a new end-host based anti-phishing algorithm, can also be called as Link Guard, by utilizing the generic characteristics of the hyperlinks in phishing attacks. These characteristics are derived by analyzing the phishing data archive provided by the Anti-Phishing Working Group. Various algorithm used for detection and defence are studied such as Naive Bayes, SVM and C0.5. The selection of the best algorithm to be implemented is based on the precision and accuracy of the algorithm in detecting the spoofed email/website effectively and protecting users privacy and liability. The propose system also discusses the effective use of Machine Learning approach in detecting the Phishing websites/ Mails that overcomes drawbacks of previously proposed And till Nonimplemented system.