A hybrid phish detection approach by identity discovery and keywords retrieval
Proceedings of the 18th international conference on World wide web
CANTINA+: A Feature-Rich Machine Learning Framework for Detecting Phishing Web Sites
ACM Transactions on Information and System Security (TISSEC)
| Hi-index | 0.00 |
In modern era, Web-based applications and services have changed the landscape of information delivery and exchange in today's corporate, government and educational arenas. An increase in the usage of web applications is directly related to the number of security threats for them. The threats leveraged through vulnerabilities, that leads to creating an attack in web applications and it will be create severe damage in online transactions. Among the various types of the website attack, phishing attack is the most common and well-known type in web application. Phishing is a cyber crime activity performed to acquire user's sensitive information such as passwords and credit card, social security, and bank account details by masquerading as a trustworthy entity in an electronic communication. This kind of threat is famous in online payment web sites, online auction and online backing web sites. In this paper we have proposed a novel approach to detect the phishing web sites by passing the user requested website address to the Google Application Programming Interface (API) to intercepting most relevance URLs (Uniform Resource Locater). The intercepted URLs are used to constructing a parse tree with the root node of requested URL. The constructed parse tree will be employed to validate the requested web site address. Identification of the phishing web site is implemented through independent web services. Our approach in a web application is independent module and it doesn't demand any change in application.