Human versus bot detection using gesture fingerprinting
Various implementations related to human versus bot detection using gesture fingerprinting are described. In one such implementation, a computer-implemented method includes receiving an input associated with an application presented on a display device, capturing sensor data associated with the input, detecting a variance in the sensor data, comparing the variance with variance criteria, determining whether the input is provided by a human user or mimicked by a programmed device based on the comparison of the variance with the variance criteria, and storing the determination as analytics data in association with the application.
1. A computer implemented method for determining an input source, the computer implemented method comprising:
receiving an input associated with an application presented on a display device;
capturing sensor data associated with the input;
detecting a variance in the sensor data, the variance being the sensor data is a deviation in the input captured in the sensor data;
comparing the variance with variance criteria, the variance criteria being a characteristic of the sensor data expected based on the input, and the variance criteria including a threshold of the deviation;
determining whether the input is provided by a human user or mimicked by a programmed device based on the comparison of the variance with the variance criteria by determining that the input is provided by the human user responsive to the deviation in the input exceeding the threshold of the deviation of the variance criteria; and
storing the determination that the input is provided by the human user as analytics data in association with the application.
2. The computer implemented method of claim 1 , wherein the input represents a touch on a touchscreen of the display device.
3. The computer implemented method of claim 1 , wherein the deviation in the input is a change in one of a direction of the input and a pressure of the input.
4. The computer implemented method of claim 1 , wherein the deviation in the input is a change in accelerometer data of the display device.
5. The computer implemented method of claim 1 , wherein detecting the variance in the sensor data further comprises:
detecting a location of the input on a touchscreen of the display device; and
comparing the location of the input on the touchscreen to a variability profile to detect the variance in the location of the input on the touchscreen.
6. A system comprising:
one or more processors; and
one or more memories storing instructions that, when executed by the one or more processors, cause the system to perform operations including:
receiving an input associated with an application presented on a display device;
capturing sensor data associated with the input;
detecting a variance in the sensor data, the variance in the sensor data being a deviation in the input captured in the sensor data;
comparing the variance with variance criteria, the variance criteria being a characteristic of the sensor data expected based on the input, and the variance criteria including a threshold of the deviation;
determining whether the input is provided by a human user or mimicked by a programmed device based on the comparison of the variance with the variance criteria by determining that the input is provided by the human user responsive to the deviation in the input exceeding the threshold of the deviation of the variance criteria; and
storing the determination that the input is provided by the human user as analytics data in association with the application.
7. The system of claim 6 , wherein the input represents a touch on a touchscreen of the display device.
8. The system of claim 6 , wherein the deviation in the input is a change in one of a direction of the input and a pressure of the input.
9. The system of claim 6 , wherein the deviation in the input is a change in accelerometer data of the display device.
10. The system of claim 6 , wherein detecting the variance in the sensor data further comprises:
detecting a location of the input on a touchscreen of the display device; and
comparing the location of the input on the touchscreen to a variability profile to detect the variance in the location of the input on the touchscreen.
11. A computer implemented method for determining an input source, the computer implemented method comprising:
receiving an input associated with an application presented on a display device, the input including a touch on a touchscreen of the display device;
capturing accelerometer data associated with the display device concurrent with receiving the input;
determining a direction of the touch on the touchscreen;
identifying a variability profile of an expected touch on the touchscreen of the display device, the variability profile including an accelerometer model and a direction model;
comparing the accelerometer data associated with the display device with the accelerometer model of the variability profile;
comparing the direction of the touch on the touchscreen with the direction model of the variability profile;
determining that the input is provided by a programmed device mimicking a human user responsive to one of the accelerometer data and the direction of the touch matching with the variability profile that represents the programmed device; and
storing the determination that the input is provided by the programmed device mimicking the human user as analytics data in association with the application.
12. The computer implemented method of claim 11 , wherein the touch on the touchscreen is one of a swipe, a tap, a pinch, and a drag on the touchscreen of the display device.
13. The computer implemented method of claim 11 , further comprising:
capturing a pressure of the input including the touch on the touchscreen of the display device; and
comparing the pressure of the input including the touch on the touchscreen to the variability profile that includes a pressure model.
14. The computer implemented method of claim 11 , wherein the variability profile is updated over time.