Sensor misbehavior detection system utilizing communications
Disclosed are systems, apparatuses, processes, and computer-readable media for wireless communications. For example, an example of a process includes detecting an object based on sensor data from at least one sensor of the network device. The process further includes receiving, by the network device, a vehicle-based message comprising message data related to the object. The process further includes comparing, by the network device, the sensor data and the message data and detecting, by the network device, malicious behavior based on the comparing.
1. A method for wireless communications at a network device, the method comprising:
receiving, by the network device, a vehicle-based message comprising message data related to an object in an environment in which the network device is located;
collecting fusion sensor data associated with the environment from a plurality of sensors, wherein sensor data of the fusion sensor data from each respective sensor of the plurality of sensors is respectively weighted based on a respective confidence level associated with a detection range of each respective sensor of the plurality of sensors, and wherein at least two sensors of the plurality of sensors have different detection ranges;
comparing, by the network device, the fusion sensor data and the message data; and
determining, by the network device, whether there is malicious behavior based on the comparing.
2. The method of claim 1 , wherein the vehicle-based message is one of a Basic Safety Message (BSM), a Cooperative Awareness Message (CAM), a Collective Perception Message (CPM), a Sensor Data Sharing Message (SDSM), a Decentralized Environmental Message (DENM), or a Signal, Phase, and Time (SPaT) message.
3. The method of claim 1 , further comprising generating, by the network device, a misbehavior report comprising information associated with detected malicious behavior.
4. The method of claim 3 , further comprising transmitting, by the network device, the misbehavior report to a misbehavior authority.
5. The method of claim 1 , further comprising:
determining incorrect information is contained within the vehicle-based message based on comparing the fusion sensor data and the vehicle-based message; and
determining there is the malicious behavior based on the incorrect information contained within the vehicle-based message.
6. The method of claim 5 , wherein the incorrect information includes at least one of a ghost object or simulated free space within the vehicle-based message.
7. The method of claim 1 , further comprising determining whether to disable or enable a first sensor of the plurality of sensors based on at least one of a status of the first sensor, a capability of the first sensor, or a characteristic of the environment.
8. The method of claim 7 , wherein the characteristic of the environment includes weather in the environment.
9. The method of claim 1 , wherein the respective confidence level of each sensor of the plurality of sensors is further associated with an operability of each sensor during weather conditions experienced by the plurality of sensors in the environment.
10. The method of claim 1 , further comprising adjusting the detection range of each sensor of the plurality of sensors based on a respective capability of each sensor of the plurality of sensors.
11. The method of claim 10 , wherein the respective capability of each sensor of the plurality of sensors is related to an operability of each sensor of the plurality of sensors during weather conditions experienced by the plurality of sensors in the environment.
12. The method of claim 1 , further comprising removing simulated objects from the fusion sensor data.
13. The method of claim 1 , wherein the comparing further comprises comparing the fusion sensor data, the message data, and map data.
14. The method of claim 13 , wherein the map data comprises at least one of satellite data or a local map.
15. The method of claim 1 , wherein the plurality of sensors include at least one of a camera, a radar sensor, or a Light Detection and Ranging (LIDAR) sensor.
16. The method of claim 1 , wherein the network device is one of a vehicle, user equipment (UE), a roadside unit (RSU), traffic infrastructure, or a drone.
17. The method of claim 1 , wherein the network device is capable of Vehicle-to-Everything (V2X) communications.
18. The method of claim 1 , further comprising:
determining there is the malicious behavior based on the object being undetected in the fusion sensor data.
19. The method of claim 1 , further comprising:
determining there is no malicious behavior based on a detection of the object in the fusion sensor data.
20. An apparatus for wireless communications, comprising:
at least one memory; and
at least one processor coupled to the at least one memory and configured to:
receive a vehicle-based message comprising message data related to an object in an environment in which the apparatus is located;
collecting fusion sensor data associated with the environment from a plurality of sensors, wherein sensor data of the fusion sensor data from each respective sensor of the plurality of sensors is respectively weighted based on a respective confidence level associated with a detection range of each respective sensor of the plurality of sensors, and wherein at least two sensors of the plurality of sensors have different detection ranges;
compare the fusion sensor data and the message data; and
determining whether there is malicious behavior based on the comparing.
21. The apparatus of claim 20 , wherein the vehicle-based message is one of a Basic Safety Message (BSM), a Cooperative Awareness Message (CAM), a Collective Perception Message (CPM), a Sensor Data Sharing Message (SDSM), a Decentralized Environmental Message (DENM), or a Signal, Phase, and Time (SPaT) message.
22. The apparatus of claim 20 , wherein the at least one processor is configured to generate a misbehavior report comprising information associated with detected malicious behavior.
23. The apparatus of claim 22 , wherein the at least one processor is configured to output the misbehavior report for transmission to a misbehavior authority.
24. The apparatus of claim 20 , wherein the at least one processor is configured to:
determine incorrect information is contained within the vehicle-based message based on comparing the fusion sensor data and the vehicle-based message; and
determine the malicious behavior based on the incorrect information contained within the vehicle-based message.
25. The apparatus of claim 24 , wherein the incorrect information includes at least one of a ghost object or simulated free space within the vehicle-based message.
26. The apparatus of claim 20 , wherein the at least one processor is configured to determine whether to disable or enable a first sensor of the plurality of sensors based on at least one of a status of the first sensor, a capability of the first sensor, or a characteristic of the environment.
27. The apparatus of claim 26 , wherein the characteristic of the environment includes weather in the environment.
28. The apparatus of claim 20 , wherein the respective confidence level of each sensor of the plurality of sensors is related to an operability of each sensor during weather conditions experienced by the plurality of sensors in the environment.
29. The apparatus of claim 20 , wherein the at least one processor is configured to adjust the detection range of each sensor of the plurality of sensors based on a respective capability of each sensor of the plurality of sensors.
30. The apparatus of claim 29 , wherein the respective capability of each sensor of the plurality of sensors is related to an operability of each sensor of the plurality of sensors during weather conditions experienced by the plurality of sensors in the environment.
31. The apparatus of claim 20 , wherein the at least one processor is configured to remove simulated objects from the fusion sensor data.
32. The apparatus of claim 20 , wherein, to compare the fusion sensor data and the message data, the at least one processor is configured to compare the fusion sensor data, the message data, and map data.
33. The apparatus of claim 32 , wherein the map data comprises at least one of satellite data or a local map.
34. The apparatus of claim 20 , wherein the plurality of sensors includes at least one of a camera, a radar sensor, or a Light Detection and Ranging (LIDAR) sensor.
35. The apparatus of claim 20 , wherein the apparatus is one of a vehicle, user equipment (UE), a roadside unit (RSU), traffic infrastructure, or a drone.
36. The apparatus of claim 20 , wherein the apparatus is capable of Vehicle-to-Everything (V2X) communications.
37. The apparatus of claim 20 , wherein the apparatus is implemented as a network device, and further comprising:
at least one transceiver configured to receive the vehicle-based message.