Abstract
Phishing is a prevalent method of deceiving unsuspecting individuals into revealing their confidential information through counterfeit websites. The primary goal of phishing website URLs is to steal personal data, such as usernames, passwords, and online banking transactions. Phishers create websites that mimic the visual and semantic aspects of legitimate sites. As technology continues to advance, phishing techniques are evolving rapidly, necessitating the implementation of anti-phishing measures for detection and prevention. Machine learning emerges as a potent tool in the fight against phishing attacks.
This paper presents an overview of the features employed for detection and the machine learning techniques utilized for this purpose. Phishing remains a popular choice for attackers due to its ease of luring victims into clicking on seemingly legitimate but malicious links, rather than attempting to breach a computer's security defenses. These malicious links, embedded within email messages, are crafted to give the impression that they lead to the impersonated organization, often incorporating the organization's logos and other legitimate content.
Introduction
A Social Engineering-based attack relies on the psychological manipulation of individuals who are deceived into taking actions or divulging confidential information. Phishing, one of the most well-known forms of social engineering attacks, aims to exploit vulnerabilities in system processes stemming from user behavior. Even if a system has robust security measures in place to protect against password theft (e.g., encrypted client-server communication), it remains susceptible to the actions of a naive user who jeopardizes system security by disclosing their password to a fraudulent website, often reached through a link embedded in an email. Phishing is a preferred tactic among attackers because it is simpler to deceive someone into clicking on a seemingly legitimate malicious link than attempting to breach a computer's defense systems. These malicious links, embedded within email messages, are carefully crafted to give the impression that they lead to an impersonated organization, often incorporating the organization's logos and other genuine content.
In this context, we delve into the characteristics of phishing domains (or fraudulent domains), the distinguishing features that set them apart from legitimate domains, the significance of detecting these domains, and the methodologies for their detection using machine learning and natural language processing techniques.
Software Requirements -Platform Choice
• Windows 7 and above
• Front-end: Jsp and Servlet
• Back-end: Mysql
Hardware Requirements
• Processor : min. intel core i3 or AMD Ryzen 3
• RAM : min 4gb
• HDD/SSD : 256gb
• Power Supply
