DETECTION OF PHISHING WEBSITE USING MACHINE LEARNING
Ms.J.Maheswari1, Ms.J.Dhivya2, Ms.S.M.Amsaveni3, Ms.S.Gayathri4
1Assistant Professor, Department of Computer Science & Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamilnadu , India
2,3,4UG Scholar, Department of Computer Science & Engineering, Dhirajlal Gandhi College of Technology, Salem, Tamilnadu , India
---------------------------------------------------------------------***---------------------------------------------------------------------
ABSTRACT - Phishing is a fraudulent practice in which scammers impersonate legitimate individuals or organizations to obtain sensitive information from unsuspecting victims. This can occur via various communication channels such as email, text messages, or social media. Phishing is a popular tactic among cybercriminals because it is easier to persuade someone to click a malicious link that appears to be authentic than it is to bypass computer security measures. One common approach used in phishing attacks is to create fake websites and emails that closely resemble legitimate ones. This is achieved by using logos, slogans, and other elements that are typically associated with the targeted organization or individual. When users click on the links provided in these emails, they are directed to fake websites where they are asked to provide sensitive information such as login credentials, bank account details, or other personal information. To detect phishing websites, machine learning models such as Random Forest, Decision Tree, and Multilayer Perceptron are utilized and compared for their accuracy and efficiency. These models analyze various features of the website URL to determine if it is a phishing website or not. Features such as the length of the URL, the presence of certain keywords, and the type of top-level domain are taken into account when analyzing the website. The existing machine learning models used to detect phishing websites have some limitations. For example, they have low latency and lack a specific user interface. Furthermore, there is a need for an effective comparison of different algorithms used for detecting phishing websites. Phishing is a dangerous and fraudulent tactic used by cybercriminals to steal sensitive information. Machine learning models are used to detect phishing websites, but there is a need for improvement in their accuracy, efficiency, and user interface. It is essential to stay vigilant and double-check the authenticity of emails, websites, and communication channels to avoid falling victim to phishing attacks.
Key Words: Phishing, cybercriminals, fake websites, malicious link, machine learning models, Random Forest, Decision Tree, Multilayer Perceptron, phishing website ,falling victim, phishing attacks.
