As item trading becomes more popular, users can change their game items ormoney into real money more easily. At the same time, hackers turn their eyes onstealing other users game items or money because it is much easier to earnmoney than traditional gold-farming by running game bots. Game companiesprovide various security measures to block account- theft attempts, but manysecurity measures on the user-side are disregarded by users because of lack ofusability. In this study, we propose a server-side account theft detectionsystem base on action sequence analysis to protect game users from malicioushackers. We tested this system in the real Massively Multiplayer Online RolePlaying Game (MMORPG). By analyzing users full game play log, our system canfind the particular action sequences of hackers with high accuracy. Also, wecan trace where the victim accounts stolen money goes.
展开▼