Description

Unscrupulous users increasingly find Online Social Networking (OSN) platforms as lucrative targets for malicious activities, such as sending spam and spreading malware. The profitability of such activities and the fact that a large portion of the OSN communication takes place over symmetric social links (e.g., Facebook) motivate attackers to connect to real users. In particular, attackers leverage the open nature of OSNs and send to legitimate users unwanted friend requests, also known as friend spam. Unwanted friend requests in online social networks, also known as friend spam, have proven to be among the most evasive malicious activities. This is evident by the fact that most OSN users experience friend spam on a substantially more frequent basis than they experience spam on their newsfeeds or other types of unwanted traffic. Besides directly annoying users, friend spam can be used to undermine social-graph-based defense schemes, which effectively bind the number of accepted Sybils to the total number of social connections between Sybils and non-Sybil users. Hence, allowing malicious accounts to effortlessly solicit friend requests to unsuspected users who may accept them, can lead to the collapse of a major defense line. In existing system, the social graph structure to isolate fakes only will be focused. These techniques rely on the assumption that fakes can befriend only few real accounts. This assumption is not valid. In this project the system proposed a VoteTrust, a scalable defense system that further leverages user-level activities. VoteTrust first uses a PageRank-style algorithm to appropriately assign the number of votes that one can cast on another node. Due to more negative votes from real users, Sybils would get low global acceptance rates and thus can be identified out.