Paper Title
A Review Of Detection Of Malicious Urls In Twitter Stream Using A Near Real Time System
Abstract
Abstract— This paper presents a survey of twitter stream which is vital for finding twitter attacks. Online social networking
has become a very popular way for users to meet and interact online. Users spend a large amount of time on popular social
network platforms such as Facebook, MySpace, or Twitter, storing and sharing a wealth of personal information. This
information, as well as the possibility of contacting billions of users, also attracts the interest of cybercriminals. Millions of
users tweeting around the world, real time systems and different types of mining tools are emerging to allow people tracking
the events and post on Twitter. Twitter allows users to discuss events and post their status, these services open opportunities
for new forms of spam. Trending topics, the most talked about trending topics on Twitter at a given point in time, have been
seen as an opportunity to generate traffic and revenue. Spammers post tweets containing typical words of a trending topic
and URLs, usually obfuscated by URL that lead users to completely unrelated websites. This kind of spam can contribute to
devalue real time search services unless mechanisms to fight and stop spammers can be found. Online social networks are
extremely popular among Internet users. Unfortunately, in the wrong hands they are also effective tools for executing spam
campaigns. So to avoid that presenting an online spam filtering system that can be deployed as a component of the online
social networks platform to inspect messages generated by users in real-time. And that reconstructs spam messages into
campaigns for classification rather than determine them individually. Although campaign identification has been used for
offline spam filtering, apply this technique to aid the online spam detection problem with low overhead. Accordingly, system
adopts a set of features that effectively distinguish and determine spam campaigns. It drops messages classified as “spam”
before they reach the intended destination, thus protecting them from various kinds of malicious aspects. Firstly collecting a
large dataset of Twitter. From that construct a large labeled collection of users, manually classified into spammers and non-
spammers. Then identify a number of characteristics related to tweet content and user social behavior, which could
potentially be used to detect spammers. Used these characteristics as attributes of machine learning process for classifying
users as either spammers or nonspammers. This strategy succeeds at detecting much of the spammers while only a small
percentage of non-spammers are misclassified. In this system investigates correlations of URL redirect chains extracted from
several tweets and forms frequently shared url. Because attackers have limited resources and usually they reuse them.
Develop methods to discover correlated URL redirect chains using the frequently shared URLs and to determine their
suspiciousness. Collect numerous tweets from the Twitter public timeline and build a statistical classifier using them.
Evaluation results show that classifier accurately and efficiently detects suspicious URLs.