Advertisement
Published in:
2018 | OriginalPaper | Chapter
PHISH-SAFE: URL Features-Based Phishing Detection System Using Machine Learning
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Today, phishing is one of the most serious cyber-security threat in which attackers steal sensitive information such as personal identification number (PIN), credit card details, login, password, etc., from Internet users. In this paper, we proposed a machine learning based anti-phishing system (i.e., named as PHISH-SAFE) based on Uniform Resource Locator (URL) features. To evaluate the performance of our proposed system, we have taken 14 features from URL to detect a website as a phishing or non-phishing. The proposed system is trained using more than 33,000 phishing and legitimate URLs with SVM and Naïve Bayes classifiers. Our experiment results show more than 90% accuracy in detecting phishing websites using SVM classifier.