Unmasking Phishing Attacks: A Content-Centric Machine Learning Defense

Abstract

Nearly all real-world processes have moved to digital platforms in recent years as a result of the Internet's unavoidable growth. Because mobile devices facilitate our connection with connected services at your convenience, there is a surge in the usage of the internet in all facets of our lives. But this inevitable growth also carries with it several security lapses, particularly for regular end users. To make things easier for them, phishing is one of the most popular attack tactics used by hackers. An innocent email or social media message is what initially starts this kind of assault, directing the victims to a malicious website. These attack types are very difficult for security administrators to identify. Consequently, a content-centric Phishing Detection strategy is suggested in this study. The idea aims to identify the optimal training models by implementing around six distinct machine learning models. According to experimental findings, the suggested methods are incredibly reliable and provide security administrators with respectable accuracy