Identification of Phishing URL using Machine Learning

Computer science engineering

The growth of the Internet has brought network security to the public's notice. One may argue that the foundation for the Internet's quick and safe development is a secure network environment. Phishing is a crucial subset of cybercrime that involves deceiving consumers into clicking on dangerous links, obtaining their personal information, and then utilising that information to pretend to log into associated accounts in order to steal money. Attack and defence are iterative problems in network security. Both phishing techniques and phishing detection technologies are continually being improved. Blacklists and whitelists are the foundation of conventional techniques for detecting phishing links, however these cannot detect newly created phishing connectionsAs a result, we must figure out how to determine whether a recently discovered link is a phishing website and increase the prediction's precision. Prediction has grown in importance as machine learning technology has matured. This article gives techniques for phishing threat assessments for websites. It begins with a discussion of the phishing life cycle, moves on to a discussion of common anti-phishing techniques, primarily focuses on identifying phishing links, and concludes with a solution that includes data collection and a thorough understanding of machine learning based on feature extraction, modelling, and performance evaluation.. This paper provides a detailed comparison of various solutions for phishing website detection. We. Compare machine learning models like logistic regression, random forest, decision tree, Xgboost, and KNeighbors and identify the efficient model among them. Identifying efficient algorithms can help use highly efficient algorithms instead of testing separately on each algorithm.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.