The studio told players this morning that it has blocked 1394 bots and banned an additional 1678 exploiters. It’s also temporarily halted sales of its $10 exclusive access packs while it sorts out the problems.
So how does IMC determine which reports are actually legitimate and which are abusive? IMC explained that it uses what it calls a “report influence index” attached to player accounts.
“If a user is reported repeatedly by others, that user is very likely to be a bot. In addition, if the reporter is an influential individual, their report is most likely valid so we can set a priority on which account to ban first. This is where the Report Influence Index (RII) comes in. In terms of numbers, a player with 10 RII has the same impact as 10 different players with 1 RII each when reporting suspicious users. Accounts with high report counts will then move to the next step of verification. Some have suggested using CAPTCHA, but that too, will be breached eventually. It puts needless restrictions on the players, so we are not considering its use. Instead, what we chose to use is a server-side classifier based on Machine Learning (ML) technique.
“The classifier uses the comprehensive activity log of a reported account to determine if it’s a bot in percentages. We will not be revealing the classifier’s exact mechanism, as it can be manipulated by violators to bypass the system. We train our classifier by constantly inputting new data. The fact that we can maintain its accuracy is its advantage, because we’re going to manually determine which factors should be considered to identify bots. The classifier’s accuracy depends on how we determine the behavior criteria, and we examine over 20 basic criteria. The machine showed 99% accuracy on our Korean server when we set the machine to output fewer false positives. If we set strictness value low, the classifier will detect more bot with lower accuracy and vice versa.
“An account that is deemed to be a bot becomes subject to restriction after a GM’s additional confirmation. If that account gets banned, then all the users who reported that account gain one RII point. However, should the reported account be declared clean, the reporter’s RII value will be negatively affected. The RII is not a simple difference between the numbers of accurate and inaccurate report counts, and the algorithm we use to determine the final RII value can be changed in the future. Therefore, you should not report bots if you’re unsure of their offense. The system can backfire on you if you’re not careful.
“For example, a player going afk while leaving a heavy object on the attack key has to be handled differently from regular bots. The classifier can deem the afk player innocent from looking at the honest play records, so afk players should not be reported using the report function as that will work against your RII. Lastly, if we’re not absolutely sure the reported account is a bot, then it will not be banned and the reporter’s RII will remain unchanged.”