期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：9
页码：14965
DOI：10.15680/IJIRCCE.2017.0509024
出版社：S&S Publications
摘要：This paper provide high security against suspicious uniform resource location in social networks.Twitter is a social network and it can be used by more number of peoples. While open the normal browser manynumber of pages are opened .In that number of pages suspicious pages and malicious pages are occur. It detect theunwanted pages based on the redirect chain and correlation of redirection chain features are extracted from thesuspicious URL.Twitter is prone to malicious tweets containing URLs for spam, phishing, and malware distribution.Twitter spam detection schemes utilize account features such as the ratio of tweets containing URLs and the accountcreation date, or relation features in the Twitter graph. These detection schemes are ineffective against featurefabrications. Since it consume much time and more resources. Conventional suspicious URL detection schemes utilizeseveral features including lexical features of URLs, URL redirection, HTML content, and dynamic behavior. Thissystem investigates correlations of URL redirect chains extracted from several tweets. Because attackers have limitedresources and usually reuse them, their URL redirect chains frequently share the same URLs. It develops methods todiscover correlated URL redirect chains using the frequently shared URLs and to determine their suspiciousness.Evaluation results show that the classifier accurately and efficiently detects suspicious URLs.
关键词：Suspicious URL; twitter; Spammer; Online Social Network; anomaly detection
