Method and apparatus for spoofing prevention

Patent metadata

Field	Value
Publication number	US-11273841-B2
Application number	US-201816137067-A
Country	US
Kind code	B2
Filing date	Sep 20, 2018
Priority date	Sep 20, 2018
Publication date	Mar 15, 2022
Grant date	Mar 15, 2022

Abstract

A method and an apparatus for detecting a spoofing attempt associated with an autonomous vehicle are provided. The method includes acquiring, via interface circuitry of the apparatus for spoofing prevention, one or more sensor data from one or more sensors. The one or more sensor data is annotated to obtain sensor information. The sensor information extracts traffic information that the one or more sensor data carries. Abnormal sensor data that fails to capture surrounding traffic information is discarded. Furthermore, a spoofing attempt is determined based on a determination that at least one inconsistent sensor data is identified. The at least one inconsistent sensor data provides different traffic information compared to other sensor data of the one or more sensor data generated by the one or more sensors. The vehicle is therefore informed to ignore a portion of the sensor information associated with the spoofing attempt when the spoofing attempt is identified.

First claim

What is claimed is:

1. A method for spoofing prevention, comprising:
acquiring, via interface circuitry installed in a vehicle, one or more sensor data generated by one or more sensors including information to identify traffic information;
annotating, via processing circuitry, the one or more sensor data to obtain sensor information, the sensor information extracting traffic information that the one or more sensor data carries, the one or more sensor data annotation being implemented by at least one of a signal processing, an image processing, and a video processing;
determining sensor data to be abnormal sensor data when the sensor data fails to capture surrounding traffic information, the sensor data having all black pixels when abnormal;
discarding the abnormal sensor data that fails to capture the surrounding traffic information;
after discarding the abnormal sensor data, determining whether the sensor data, other than the discarded abnormal sensor data, is part of a spoofing attempt by comparing the sensor data to sensor data from multiple sensors to determine whether the sensor data is inconsistent with the sensor data from the multiple sensors, the sensor data being determined to be inconsistent with the sensor data from the multiple sensors when traffic information therein differs from traffic information in the sensor data from the multiple sensors, the sensor data and the sensor data from the multiple sensors being contemporaneously generated;
informing, via the interface circuitry, the vehicle to ignore a portion of the sensor information that is associated with the spoofing attempt when the spoofing attempt is identified,
wherein the comparing the sensor information and the traffic reference information includes comparing signal intensity, signal frequency, signal period, signal amplitude, signal rise and fall times, source location, and minimum and maximum values between the sensor data and the traffic reference information, and
the abnormal sensor data is generated by either a sensor that is malfunctioning or a sensor that is attacked.

2. The method of claim 1 , further comprising:
notifying the spoofing attempt to a driver of the vehicle, a vehicle owner, an external service, police, or parents of children in the vehicle via a display, a speaker, or a communication device.

3. The method of claim 1 , wherein acquiring the one or more sensor data from the one or more sensors includes acquiring the sensor data from at least one of a camera, a sonar sensor, a radar sensor, and a LIDAR (Light Detecting and Ranging) sensor.

4. The method of claim 1 , wherein the one or more sensors are either primary sensors installed originally for autonomous driving or redundant sensors spaced a distance apart from the primary sensors.

5. The method of claim 3 , further comprising:
acquiring a first sensor data from a primary sensor;
acquiring a second sensor data from a redundant sensor; and
determining a spoofing attempt based on a determination that the first sensor data from the primary sensor is inconsistent with the second sensor data from the redundant sensor.

6. The method of claim 1 , wherein the traffic information that the one or more sensor data carries includes at least one of a position of the vehicle, a movement speed of the vehicle, a movement direction of the vehicle, positions of adjacent objects, movement speeds of adjacent objects, movement directions of adjacent objects, a road condition, a traffic signal, and a road obstacle.

7. The method of claim 1 , wherein the abnormal sensor data is generated by either a sensor that is malfunctioning or a sensor that is attacked.

8. The method of claim 1 , further comprising updating the traffic reference information with the portion of the sensor information associated with the potential hazard.

9. A method for spoofing prevention, comprising:
acquiring, via interface circuitry installed in a vehicle, one or more sensor data generated by one or more sensors including information to identify traffic information;
annotating, via processing circuitry, the one or more sensor data to obtain sensor information, the sensor information extracting traffic information that the one or more sensor data carries, the one or more sensor data annotation being implemented by at least one of a signal processing, an image processing, and a video processing;
determining whether sensor data is abnormal sensor data that fails to capture surrounding traffic information, the sensor data having all black pixels when abnormal;
discarding the abnormal sensor data that fails to capture surrounding traffic information;
acquiring, via the interface circuitry, traffic reference information from a database;
after discarding the abnormal sensor data, comparing, using the processing circuitry, the sensor data, other than the discarded abnormal sensor data, with the traffic reference information;
after discarding the abnormal sensor data, identifying, using the processing circuitry, whether the sensor data, other than the discarded abnormal sensor data, is part of a spoofing attempt based on the comparison between the sensor data and the traffic reference information, the spoofing attempt being identified when a portion of the sensor data differs from the traffic reference information that is contemporarily generated with acquisition of the sensor data; and
informing, via the interface circuitry, the vehicle to ignore the portion of the sensor information that is associated with the spoofing attempt when the spoofing attempt is identified,
wherein the comparing the sensor information and the traffic reference information includes comparing signal intensity, signal frequency, signal period, signal amplitude, signal rise and fall times, source location, and minimum and maximum values between the sensor data and the traffic reference information, and
the abnormal sensor data is generated by either a sensor that is malfunctioning or a sensor that is attacked.

10. The method of claim 9 , further comprising:
performing machine learning on the sensor data and updating the traffic reference information with the portion of the sensor data that is associated with the spoofing attempt.

11. The method of claim 9 , wherein identifying the spoofing attempt further comprises:
comparing the sensor and the traffic reference information;
identifying at least one inconsistent sensor data based on the comparison between the sensor data and the traffic reference information, the at least one inconsistent sensor data providing different traffic information compared to the traffic reference information; and
determining the spoofing attempt based on a determination that the at least one inconsistent sensor data is identified.

12. An apparatus for spoofing prevention, comprising:
one or more sensors, the one or more sensor installed in a vehicle and configured to generate one or more sensor data, the one or more sensor data carrying traffic information that the vehicle encounters during driving; and
processing circuitry configured to:
acquire, via interface circuitry, the one or more sensor data from the one or more sensors;
annotate the one or more sensor data to obtain sensor information, the sensor information extracting the traffic information that the one or more sensor data carries, the one or more sensor data annotation being implemented by at least one of a signal processing, an image processing, and a video processing;
determine whether sensor data is abnormal sensor data that fails to capture surrounding traffic information, the sensor data having all black pixels when abnormal;
discard the abnormal sensor data that fails to capture the

Assignees

• Toyota Res Inst Inc

Inventors

• Goldman Ron

Classifications

• G01S17/931 Primary

  of land vehicles · CPC title

• B60W2050/0215

  Sensor drifts or sensor failures · CPC title

• G08G1/09623

  Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle (G08G1/0967 takes precedence) · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• B60W60/00188

  related to detected security violation of control systems, e.g. hacking of moving vehicle · CPC title