Pediredla Swamy, Dr. Kunjam Nageswara Rao (Professor) & Kalidindi Venkateswara Rao
Andhra University, Visakhapatnam.

Dr. G. Sita Ratnam (Associate Professor)
LENDI Institute of Engineering and Technology, Vizianagaram.


Phishing is one in all the foremost common and dangerous attacks among cybercrimes. The victim’s confidential knowledge is predicted by the phishing sites by derivation them to surf a phishing web site that resembles to legitimate web site, that is one in all the criminal attacks prevailing within the net. Phishing websites is comparable to cyber threat that’s targeting to induce all the credential-based data like data accessed from the credit cards and Social Security numbers. The aim of this project is to perform Extreme Learning Machine (ELM) primarily based classification for thirty options as well as Phishing Websites knowledge in University of California (UC) Irvine Machine Learning Repository information. There are differing kinds of options supported sites. Hence, to forestall phishing attacks there is tendency to use a particular web content feature. The project model supports machine learning techniques like Naïve Bayes, Linear Discriminant Analysis (LDA) and Support Vector Machine to discover phishing sites. For results assessment, ELM was compared with different machine learning ways like Support Vector Machine (SVM), Naïve Bayes (NB), Linear Discriminant Analysis (LDA) and detected to possess the 96.74% accuracy.