Volume : III, Issue : V, May - 2014

An Improved Technique for Detecting Suspicious Urls in Twitter Stream

Adithya. N. P. , Ginnu George

Abstract :

Social networking sites have become very popular in recent years. Among these sites, Twitter is the fastest growing site. Because of its popularity, Twitter is prone to malicious tweets containing URLs for spam, phishing, and malware distribution. Conventional Twitter spam detection schemes utilize account features such as the ratio of tweets containing URLs and the account creation date, or relation features in the Twitter graph. These detection schemes are ineffective against feature faications or consume much time and resources. Conventional suspicious URL detection schemes utilize several features including lexical features of URLs, URL redirection, HTML content, and dynamic behavior. However, evading techniques such as time–based evasion and crawler evasion exist. This paper proposes an improved technique for detecting suspicious URLs in Twitter stream. This system investigates correlations of URL redirect chains extracted from several tweets. Because attackers have limited resources and usually reuse them, their URL redirect chains frequently share the same URLs.  In order to discover correlated URL redirect chains using the frequently shared URLs and to determine their suspiciousness some methods are developed. Numerous tweets from the Twitter public timeline are collected and build a statistical classifier using them. Using these classifier phishing URLs are detected. Evaluation results show that this classifier accurately and efficiently detects suspicious URLs

Keywords :

Article: Download PDF   DOI : 10.36106/ijsr  

Cite This Article:

Adithya.N.P., Ginnu George An Improved Technique for Detecting Suspicious Urls in Twitter Stream International Journal of Scientific Research, Vol.III, Issue. V, May 2014

Number of Downloads : 803

References :