A novel framework to preserve privacy in online social networks

Abstract

Online Social Networks (OSNs) are crucial parts of virtual world that connects people and provides all real-time elements like news, opinions and other data. In this social networking era, an improved quantity of novel data has been reached with dissimilar viewpoints in an unexpected manner. Moreover, the needful data propagation is reached in OSNs will deliver false data or rumour information. This will cause damage to society in a negative aspect and divert them from exact contents as actual; rumour spreads quicker than the exact content in OSNs. So, knowing the space and stance are the needful research content in this modern era. The aim of this thesis is to enhance the reliability of OSNs contents by discovering and controlling the spam. newlineSpam detection in OSNs is an emerging research area aiming to increase accuracy and minimize suspicious attacks, especially on Twitter. The feature set has been developed for analyzing the tweets whiles the following relationship in category-based malicious behaviour detection techniques. The features can be utilized to know the malicious profile that will increase the system performances. Many existing techniques have failed to provide high amount of accuracy and spam detection rate. Online Social Networks (OSNs) are utilized by millions of people around the world to communicate with others through Online Social networks like Facebook and Twitter. The removal of fake accounts will increase the efficiency of protection in OSNs. The construction of OSN model has nodes and links to identify the fake profiles on Twitter. A novel technique is proposed to detect spam profiles and the proposed classifier is to classify the profile images from the dataset newline