Using keystroke and mouse dynamics for user identification in the online collaborative game League of Legends

© 2016 Institution of Engineering and Technology. All rights reserved. The popularity of computer games has grown exponentially in the last few years. It is not uncommon to find players of online games who can dedicate their whole lives in order to became the best in their favourite game. The best players normally become celebrities and can even get sponsored to compete in game tourneys. It is accepted that each player should follow the his/her own path to increase level, so the experience reflected in the gamer's level is how proficient he/she is in the game. However, this increased popularity has also created a desire on some players to cheat (by paying others more experienced players to play for them) for the progress in the game and thus to improve their status. The companies that develop such games have very strict punishment for such breaking of the rules, but, it can be very difficult to identify when this "account sharing" happens. This paper focus on the collection and analysis of a new online game database for continuous mouse dynamics and keystroke dynamics authentication in order to identify whether who is playing is really the account holder. Our very first results point to very interesting possibilities for security biometric-based applications in this new game analysis area.