ALGORITHM BASED DETECTION OF MALICIOUS URLS FOR ENHANCED CYBERSECURITY

Abstract

Phishing websites have proven to be a major security concern. Several cyber-attacks risk the confidentiality, integrity, and availability of company and consumer data, and phishing is the beginning point for many of them. Phishing is an internet scam in which an attacker sends out fake messages that look to come from a trusted source. A URL or file will be included in the mail, which when clicked will steal personal information or infect a computer with a virus. Traditionally, phishing attempts were carried out through wide-scale spam campaigns that targeted broad groups of people indiscriminately. The goal was to get as many people to click on a link or open an infected file as possible. There are various approaches to detect this type of attack. One of the approaches is machine learning. The URL’s received by the user will be given input to the machine learning model then the algorithm will process the input and display the output whether it is phishing or legitimate. There are various ML algorithms like SVM, Neural Networks, Random Forest, Decision Tree, XG boost etc. that can be used to classify these URLs. By extracting and comparing different characteristics between legitimate and phishing URLs, the suggested method uses gradient boosting classifier to identify phishing URLs. The studies’ findings demonstrate that the suggested approach successfully identifies legitimate websites from bogus ones in real time