Improving Phishing URL Detection Using Fuzzy Association Mining
M. Nivedha, Mr. S. Gokulan, Mr. C. Karthik, Mr. A. Gopinath, Mr.R. Gowshik · The International Journal of Engineering and Science · 2017
Phishing is the process to obtain sensitive information such as usernames, passwords, and credit card details by disguising as a trustworthy entity by the use of an electronic communication.Phishing attack continues to pose a solemn risk for web users and annoying threat within the field of electronic commerce.The Phishing detection using fuzzy and binary matrix construction method focuses on discerning the significant features that discriminate between legitimate and phishing URLs.The significant features are extracting the number of dots, length of the host etc., from each URL.These features are then subjected to associative rule mining-apriori and predictive apriori.The rules obtained are interpreted to emphasize the features that are more prevalent in phishing URLs.The key factors for the phished URLs are number of slashes in the URL, dot in the host portion of the URL and length of the URL.The pitfall of binary matrix method is the time complexity.So it impacts the overall speed of the system.The fuzzy based logic association rule mining algorithm was proposed to classify the legitimate and phishing URLs based on the features.The extracted features are converted to fuzzy membership values as "Low",' Medium' and "High".By applying association rule mining algorithm the rules are generated to detect the phishing URLs.The fuzzy based methodology provides efficient and high rate of phishing detection of URLs.