ProGuard: Detecting Malicious Accounts in Social-Network-Based Online Promotions

Abstract

Online social networks gradually integrate financial capabilities by enabling the usage of real and virtual currency. They serve as new platforms to host a variety of business activities such as online promotion events, where users can possibly get virtual currency as rewards by participating such events. Both OSNs and business partners are significantly concerned when attackers instrument a set of accounts to collect virtual currency from these events, which make these events ineffective and result in significant financial loss. It becomes of great importance to proactively detecting these malicious accounts before the online promotion activities and subsequently decrease their priority to be rewarded. In this paper, we propose a novel system, namely ProGuard, to accomplish this objective by systematically integrating features that characterize accounts from three perspectives including their general behaviors, their recharging patterns, and the usage of their currency. We have performed extensive experiments based on data collected from Tencent QQ, a global leading OSN with built-in financial management activities. Experimental results have demonstrated that our system can accomplish a high detection rate of 96.67% at a very low false positive rate of 0.3%.

Existing System

Proposed System

Architecture