A Machine Learning Approach for Game Bot Detection Through Behavioural Features

In the last years, online games market has been interested by a sudden growth due to the birth of new gaming infrastructures that offer more effective and innovative services and products. Simultaneously to the diffusion of on line games, there was an increasing use of game bots to automatically perform malicious tasks. Game bots users aim to obtain some rewards by automating the most tedious and prolonged activities arousing the disappointment of the game community. Therefore, the detection and the expulsion of game bots from the game environment, become critical issues for the game’s developers that want to ensure the satisfaction of all the players. This paper describes an approach for the game bot detection in the online role player games consisting to distinguish between game bots and human behavior and based on the adoption of supervised and unsupervised machine learning techniques. These techniques are used to discriminate between users and game bots basing on some user behavioral features. The approach is applied to a real-world dataset of a popular role player game and the obtained results are encouraging.