Abstract: Phishing is the combination of social engineering and technical exploits designed to convince a victim to provide personal information, usually for the economic gain of the attacker. Phishing emails contains messages to attract victims into performing certain actions, such as checking the URL where a phishing website is hosted and executing a malware code for future use. Phishing has become the most popular practice among the criminals of the Web. Phishing is a continual threat that keeps growing to this day. URL and textual content analysis of email will results in a highly accurate anti phishing email classifier and prevention of them. We will propose a technique where we consider the advantages of blacklist, white list and combination of both that means heuristic technique for increasing accuracy and reducing false positive rate as well as true negative rate. In heuristic technique we are using textual analysis and URL analysis of e-mail and domine analysis.. Since most of the phishing mails have similar contents, our proposed method Bait Alarm will increase the performance by analysing textual contents of email and lexical contains of URL analysis. It will detect phishing mail if DNS is present in black list and If DNS is present in white list then it is considered as authorized DNS. If it is not present in white list as well as blacklist then it is analyzed by using pattern matching with existing phishing DNS test and contents found in email and analysis of actual URL analysis. With the help white list and black list we are avoiding detection time for phishing and authorized email. At the same time we are decreasing false positive rate by combining features of DNS, pattern matching, textual content analysis of email and URL analysis.
Keyword: Anti-phishing, Network Security, Hyperlink, iFrame, Phishing, URLObfus-cation.
Title: Bait Alarm: Anti-Phishing Using Visual Similarities
Author: Anuja Salve, Manisha Salgar, Akshata Sarode, Trushali Sardal, Prof. Archana Said
International Journal of Engineering Research and Reviews
ISSN 2348-697X (Online)
Research Publish Journals
