Surgical strike: A novel approach to minimize collateral damage to game BOT detection

Recently, real money trading (RMT) by gold farming groups (GFGs) in online games has increased. In particular, GFGs in massively multiplayer online role playing games (MMORPGs) illegally gather and distribute virtual goods and sell them for real money. The previous methods for GFG detection have focused on the user's behavior analysis, but they could detect only gold farmers, not whole GFGs. In this study, we focused on the virtual economy in games and traced abnormal trade networks formed by the gold farmers. We evaluated this method in a real game, AION, the third largest MMORPG. As a result, we can detect not only gold farmer characters but also the entire network structure of GFGs.