Deep Learning for Phishing Website Detection

Abstract

Data security has become a major issue as digitalization across the world is rapidly increasing. Personal information of the user is extracted and exploited using one of the cyber-attack known as phishing. To detect phishing, and to avoid the user from visiting a non-legitimate website, a method is proposed in this paper. This method uses unique features of Uniform Resource Locator which can differentiate between legitimate and non-legitimate websites. To classify websites, Random forest and Support Vector Machines are two machine learning methods that are employed in this work. The internet offers a wealth of information that may be accessed. Because of the rapid development of technology, an unavoidable dependency on the Internet has emerged in all aspects of life. As the number of apps that run on the Internet continues to rise, there is also a rising worry of threats and a need to address problems that are connected to security. There are numerous web application threats in the Internet domain. These threats aim to either steal sensitive information from users, change the database of web servers, or undermine the credibility of a particular web application. There are many web application threats in the Internet domain. These threats include: One of the most significant dangers to information security is the character. Attacks that Deny Service to Others Session Hijacking attempts The CrossSite Scripting Language XSS Phishing and Buffer Overflow are Two Common Scams Phishing is one of these methods, and it involves tricking people into giving sensitive information such as usernames and passwords, credit card details, and sensitive bank information by way of email spoofing, instant messaging, or fake web sites whose look and feel give the appearance of a legitimate one. Examples of such information include usernames and passwords for online accounts, credit card details, and sensitive bank information. Important forms of phishing include deceptive phishing, malware-based phishing, host file poisoned content, and others. injection phishing through man-in-the-middle attacks, phishing via search engines, and phishing via social engineering Due to the fact that phishing may cause significant losses, it is necessary to implement new line processes in order to identify and stop phishing attacks. At this time, there are a number of techniques for detecting phishing. Some of these methods include blacklisting and whitelisting, visual resemblance, content-based approaches, and detecting phishing.