Submovement-based mouse input cheating detection
A cheat detection methodology is disclosed that relates to identifying cheaters making super-human movements in interactive programs. For example, users trying to outcompete their opponents in video games using large aim assists and aim bots that perform actions that are not feasibly human. The disclosed methodology substantially reduces or even eliminates the benefit that various cheating solutions offer. In one aspect, the disclosure provides a method of monitoring cheating in interactive programs. In one example, the method includes: (1) obtaining motion data corresponding to a user input device responding to an interactive program, (2) segmenting data submovements from the motion data, and (3) determining data submovements that are a deviation of human submovements.
1 . A method of monitoring cheating in interactive programs using one or more processors, comprising:
obtaining motion data corresponding to a user input device interacting with an interactive program;
segmenting data submovements from the motion data, wherein the data submovements are decompositions of the motion data; and
determining data submovements that deviate from human submovements based on a derivative of a velocity of the data submovements, wherein the derivative of the velocity includes acceleration of the data submovements and the deviation is determined when the acceleration is constant.
2 . The method as recited in claim 1 , wherein the input device is a mouse.
3 . The method as recited in claim 1 , wherein the input device is a spatially tracked controller.
4 . The method as recited in claim 1 , wherein the motion data is positional information over time.
5 . The method as recited in claim 1 , wherein the segmenting uses start and stop thresholds to detect the data submovements from the motion data.
6 . The method as recited in claim 5 , wherein the start and stop thresholds are based on the interactive program.
7 . The method as recited in claim 1 , wherein the segmenting uses wavelet decomposition to detect the data submovements from the motion data.
8 . The method as recited in claim 1 , wherein the deviation is further based on a duration of one or more of the data submovements.
9 . The method as recited in claim 1 , wherein the deviation is further based on a number of data submovements for an action.
10 . The method as recited in claim 9 , wherein an action is a response to detection of a target.
11 . The method as recited in claim 9 , wherein the deviation is determined when the number of data submovements is one.
12 . The method as recited in claim 1 , wherein the deviation is further determined when a shape of the data submovements is not a ballistic shape.
13 . The method as recited in claim 1 , wherein the deviation is further based on a distribution of the data submovements compared to a general statistical model.
14 . The method as recited in claim 1 , wherein the deviation is further based on a distribution of the data submovements compared to a user specific statistical model.
15 . The method as recited in claim 1 , wherein the human submovements are for a particular user.
16 . The method as recited in claim 1 , wherein the interactive program is a video game.
17 . The method as recited in claim 1 , further comprising generating an alert of possible cheating when determining the deviation.
18 . A cheat alert system for one or more interactive programs, comprising:
one or more processors to perform operations at least including:
segmenting data submovements corresponding to an input device, wherein the data submovements are decompositions of the motion data from the input device; and
detecting data submovements that deviate from human submovements based on a derivative of a velocity of the data submovements, wherein the derivative of the velocity is jerk present in maximum rate acceleration or deceleration curves of the data submovements.
19 . The cheat alert system as recited in claim 18 , wherein the operations further include reporting potential cheating based on the detecting.
20 . The cheat alert system as recited in claim 18 , wherein the detecting is further based on a duration of one or more of the data submovements or a number of submovements for an action.
21 . The cheat alert system as recited in claim 18 , wherein the detecting is further based on a distribution of the data submovements compared to a user specific statistical model or a general statistical model.
22 . The cheat alert system as recited in claim 18 , wherein the detecting is further based on a combination of attributes of the data submovements.
23 . A gaming system, comprising:
one or more processors that perform operations at least including:
receiving motion data from an input device;
segmenting data submovements from the motion data, wherein the data submovements are decompositions of the motion data; and
detecting data submovements that deviate from human submovements based on a derivative of a velocity of the data submovements, wherein the derivative of the velocity is jerk present in maximum rate acceleration or deceleration curves of the data submovements.
24 . The gaming system as recited in claim 23 , wherein the operations further include generating an alert of possible cheating when determining the deviation.
25 . The gaming system as recited in claim 23 , wherein the derivative of the velocity is acceleration of the data submovements.