Phishing Websites Classification using Hybrid SVM and KNN Approach

Abstract

Phishing is a potential web threat that includes mimicking official websites to trick users by stealing their important information such as username and password related to financial systems. The attackers use social engineering techniques like email, SMS and malware to fraud the users. Due to the potential financial losses caused by phishing, it is essential to find effective approaches for phishing websites detection. This paper proposes a hybrid approach for classifying the websites as Phishing, Legitimate or Suspicious websites, the proposed approach intelligently combines the K-nearest neighbors (KNN) algorithm with the Support Vector Machine algorithm (SVM) in two stages. Firstly, the K-NN was utilized as and robust to noisy data and effective classifier. Secondly, the SVM is employed as powerful classifier. The proposed approach integrates the simplicity of KNN with the effectiveness of SVM. The experimental results show that the proposed hybrid approach achieved the highest accuracy of 90.04% when compared with other approaches.