System and method of cheat detection in video games
A system and method may detect cheating in a computer game, by receiving inputs to a computer game from an entity (which may be a cheater or bot; or a human), comparing the inputs from the entity to data related to inputs to a computer game from human players, and based on the comparing, determining if the entity is a human player or a cheater. The comparing may be based on performance metrics derived from the inputs, and may be by statistical analysis or, comparing a statistical distribution.
1. A method of detecting cheating in a computer game, the method comprising:
receiving a plurality of inputs to a computer game from a plurality of human players;
receiving a plurality of inputs to the computer game from an entity;
computing performance metrics based on the plurality of inputs from the plurality of human players;
computing performance metrics based on the plurality of inputs from the entity;
characterizing a statistical distribution of the performance metrics from the plurality of human players;
characterizing a statistical distribution of the performance metrics from the entity;
comparing the performance metrics from the plurality of inputs from the entity to the performance metrics from the plurality of inputs from the plurality of human players, wherein the comparing comprises comparing the statistical distribution of performance metrics from the entity to the statistical distribution of performance metrics from the plurality of human players; and
based on the comparing, determining if the entity is a human player or a cheater.
2. The method of claim 1 , wherein the performance metrics are selected from the group consisting of: movement kinematics, movement amplitude, movement speed, accuracy of movement landing point, movement reaction time, reaction time between target appearance and initiation of a movement, swipiness, movement variability, movement precision, motor acuity, speed-accuracy trade-off, proportion of movements for which there is no shot, number corrective movements to hit a target, shot performance, shot time, shot speed, shot error, shot variability, shot precision, number of shots to hit a target, and proportion of targets for which the player hits the target.
3. The method of claim 1 , wherein the one or more inputs are provided by an input device selected from the group consisting of: computer mouse, keyboard, mobile computing device, mobile telephone, mobile device, and game controller.
4. The method of claim 1 , comprising, if it is determined that the entity is a cheater, taking action from the group consisting of: informing other entities that the entity is a cheater; stopping the play of the entity; adding the entity's username to a list of cheaters; removing the entity from a leaderboard; banning the entity from the game; freezing the account of the entity; and undoing effects the entity's actions have had on other entities.
5. The method of claim 1 , wherein the entity is a human player, or a bot providing input, and determining that the entity is a cheater indicates the entity is a bot.
6. The method of claim 1 , comprising, if it is determined that the entity is a player using a bot, taking action from the group consisting of: informing other entities that the entity is a cheater; stopping the play of the entity; adding the entity's username to a list of cheaters; removing the entity from a leaderboard; banning the entity from the game; freezing the account of the entity; and undoing effects the entity's actions have had on other entities.
7. The method of claim 1 , wherein the comparing comprises calculating a likelihood that the statistical distribution of the performance metrics from the entity corresponds to human input represented by the statistical distribution of performance metrics from the plurality of human players; and the entity is determined to be a cheater if the likelihood is below a threshold.
8. The method of claim 1 , wherein the comparing comprises calculating a distance between the statistical distribution of the performance metrics from the entity and the statistical distribution of the performance metrics from the plurality of human players; and the entity is determined to be a cheater if the distance is greater than a threshold.
9. The method of claim 1 , wherein the comparing comprises a comparison of two probability density functions.
10. The method of claim 1 , wherein each statistical distribution is created based on a probability density.
11. The method of claim 1 , wherein each statistical distribution is a multivariate distribution.
12. A system for detecting cheating in a computer game, the system comprising:
a memory; and
a processor to:
receive a plurality of inputs to a computer game from a plurality of human players;
receive a plurality of inputs to the computer game from an entity;
compute performance metrics based on the plurality of inputs from the plurality of human players;
compute performance metrics based on the plurality of inputs from the entity;
characterize a statistical distribution of the performance metrics from the plurality of human players;
characterize a statistical distribution of the performance metrics from the entity;
compare the performance metrics from the plurality of inputs from the entity to the performance metrics from the plurality of inputs from the plurality of human players, wherein the comparing comprises comparing the statistical distribution of performance metrics from the entity to the statistical distribution of performance metrics from the plurality of human players; and
based on the comparing, determine if the entity is a human player or a cheater.
13. The system of claim 12 , wherein the performance metrics are selected from the group consisting of: movement kinematics, movement amplitude, movement speed, accuracy of movement landing point, movement reaction time, reaction time between target appearance and initiation of a movement, swipiness, movement variability, movement precision, motor acuity, speed-accuracy trade-off, proportion of movements for which there is no shot, number corrective movements to hit a target, shot performance, shot time, shot speed, shot error, shot variability, shot precision, number of shots to hit a target, and proportion of targets for which the player hits the target.
14. The system of claim 12 , wherein the one or more inputs are provided by an input device selected from the group consisting of: computer mouse, keyboard, mobile computing device, mobile telephone, mobile device, and game controller.
15. The system of claim 12 wherein the processor is to, if it is determined that the entity is a cheater, take action from the group consisting of: informing other entities that the entity is a cheater; stopping the play of the entity; adding the entity's username to a list of cheaters; removing the entity from a leaderboard; banning the entity from the game; freezing the account of the entity; and undoing effects the entity's actions have had on other entities.
16. The system of claim 12 , wherein the entity is a human player, or a bot providing input, and determining that the entity is a cheater indicates the entity is a bot.
17. A method of detecting cheating in a computer game, the method comprising:
receiving a plurality of inputs to a computer game from a plurality of human players;
receiving a plurality of inputs to the computer game from an entity;
computing performance metrics based on the plurality of inputs from the plurality of human players;
computing performance metrics based on the plurality of inputs from the entity;
creating a statistical distribution of the performance metrics from the plurality of human players;
creating a statistical distribution of the performance metrics from the entity;
comparing the statistical distribution of performance metrics based on the inputs from the entity to the statistical distribution of performance metrics from the plurality of human players; and
based on the comparing, determining if the entity is a human player or a player using a bot.
18. The method of claim 17 , wherein the performance metrics are selected from the group consisting of: movement kinematics, movement amplitude, movement speed, accuracy of movement landing point, movement reaction time, reaction time between target appearance and initiation of a movement, swipiness, movement variability, movement precision, motor acuity, speed-accuracy trade-off, proportion of movements for which there is no shot, number corrective movements to hit a target, shot performance, shot time, shot speed, shot error, shot variability, shot precision, number of shots to hit a target, and proportion of targets for which the player hits the target.
19. The method of claim 17 , wherein the inputs are provided by an input device selected from the group consisting of: computer mouse, keyboard, mobile computing device, mobile telephone, mobile device, and game controller.
20. The method of claim 17 , wherein each statistical distribution is a probability density function.