Online Social Networks (OSN) gradually integrates 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 decreases 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.
• Existing methods on detecting spamming accounts in OSNs, it is faced with new challenges to detect malicious accounts that participate in online promotion activities.
• First, different from spamming accounts, these accounts neither rely on spamming messages nor need malicious network infrastructures to launch attacks.
• Second, social structures are not necessary. Therefore, none of existing methods is applicable to detecting malicious accounts in online promotion activities. To solve the new challenges, our method detects malicious accounts by investigating both regular activities of an account and its financial activities.
• These two challenges make the detection of such malicious OSN accounts fundamentally different from the detection of traditional attacks such as spamming and phishing.
• None of the method is applicable to detect malicious accounts in online promotion activities
• Our objective is to design a detection system capable of identifying malicious accounts that participate in online promotion events for virtual currency collection before rewards are committed.
• Detecting malicious accounts at this specific time point results in unique advantages.
• First, as a simple heuristic to prevent freshly registered accounts that are likely to be bots, business entities usually require the participating accounts to be registered for a certain amount of time.
• Therefore, the detected and mitigated malicious accounts cannot be immediately replaced by the newly registered accounts, thereby drastically limiting attackers’ capabilities.
• Second, our detection system will label whether an account is malicious when it participates in an online promotion event; this enables business entities to make actionable decisions such as de-prioritize this account from being rewarded in this event.
• Accuracy for detection is high.
In this project using Three Algorithms. They are,
1. Logistic Regression,
2. Decision Trees, and
3. Artificial Neural Networks.
System : Pentium IV 2.4 GHz.
Hard Disk : 40 GB.
Floppy Drive : 1.44 Mb.
Monitor : 15 VGA Colour.
Mouse : Logitech.
Ram : 2 Gb.
Operating system : Windows XP/7.
Coding Language : ASP.Net, C#.net
Tool : Visual Studio 2012
Database : SQL SERVER 2008
Y. Wang and S. D. Mainwaring, “Human-currency interaction: learning from virtual currency use in china,” in Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM, 2008,pp. 25–28.