US 12,269,424 B2
Unauthorized access detection
Emad S. Isaac, Downers Grove, IL (US)
Assigned to Allstate Insurance Company, Northbrook, IL (US)
Filed by Allstate Insurance Company, Northbrook, IL (US)
Filed on Jul. 23, 2020, as Appl. No. 16/937,006.
Prior Publication US 2022/0024414 A1, Jan. 27, 2022
Int. Cl. B60R 25/25 (2013.01); B60R 25/24 (2013.01); B60R 25/32 (2013.01); G06N 20/00 (2019.01); G06V 40/50 (2022.01); B60R 25/102 (2013.01); B60R 25/33 (2013.01)
CPC B60R 25/252 (2013.01) [B60R 25/241 (2013.01); B60R 25/32 (2013.01); G06N 20/00 (2019.01); G06V 40/50 (2022.01); B60R 25/102 (2013.01); B60R 25/33 (2013.01)] 18 Claims
OG exemplary drawing
 
1. An apparatus implemented in a vehicle, the apparatus comprising:
at least one sensor configured to measure a characteristic of the vehicle;
at least one processor;
a communication interface communicatively coupled to the at least one processor; and
memory storing non-transitory computer-readable instructions that, when executed by the processor, cause the apparatus to:
receive sensor data aggregated by the at least one sensor while the vehicle is being driven by a first driver in one or more plurality of modes of operation, wherein the sensor data indicates one or more of: a speed of the vehicle, a distance that the vehicle is driven, a rate of acceleration, a rate of braking of the vehicle, or a swerving of the vehicle;
generate, based at least in part on the received sensor data, a first vehicle fingerprint indicative of driving characteristics associated with the first driver;
after generating the first vehicle fingerprint, receive additional sensor data aggregated by the at least one sensor while the vehicle is being driven;
identify an expected driving characteristic of the vehicle for a mode of operation of the one or more plurality of modes of operation;
determine, based on the received additional sensor data, an actual driving characteristic of the vehicle for the mode of operation;
compute a difference score indicating a difference between the expected driving characteristic and the actual driving characteristic;
generate, based at least in part on the received additional sensor data and the computed difference score, a second vehicle fingerprint by applying a machine learning model to the first vehicle fingerprint; and
after determining that a deviation exists between first vehicle fingerprint and the second vehicle fingerprint, providing an alert to the communication interface indicating a potential unauthorized use of the vehicle.