WEBSITE PHISING DETECTION APPLICATION USING SUPPORT VECTOR MACHINE (SVM)

Phishing is an act to get someone's important information in the form of usernames, passwords, and other sensitive by providing fake websites that are similar original. (fishing for information) a criminal intends obtain confidential from someone, such as passwords credit cards, impersonating trusted person or business official electronic communication, mail instant messages. Along with development use media, which followed increase cyber crime, this phishing attack. Therefore, minimize attacks, system needed can detect these attacks. Machine Learning one method be used create phishing. The data research 11055 website data, divided into two classes, namely "legitimate" "phishing". This then using 10-fold cross validation. While algorithm Support Vector (SVM) compared decision tree k-nearest neighbor algorithms optimizing parameters each algorithm. From test results study, best accuracy was 85.71% SVM kernel polynomial values degree 9 C 2.5.