Autonomous Driving Spoofing Detection Using Mapped Static Objects
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles (ADVs) are vulnerable to cyber-attacks and spoofing attacks that can manipulate their routes or sensor information, posing risks to safety and efficiency, with existing mitigation measures being costly and not easily adaptable to changing threats.
Innovation Solution
The use of pre-defined static objects on a high-definition map as ground truth points to detect and counter cyber-attacks and spoofing attacks, by verifying sensor coverage and analyzing route changes, and leveraging machine learning to identify abnormal re-routing or sensor impairments, with the option to exclude impaired sensors and alert passengers or service providers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ADVs use enhanced sensor robustness and improved perception algorithms to mitigate spoofing attacks, then security reliability is improved, but device complexity and implementation cost increase
Solution Approach 1:
The patent introduces map data as an intermediary reference system that mediates between sensor inputs and navigation decisions. By comparing sensor-detected objects against pre-stored map data, the system creates a verification layer that detects spoofing without requiring complex sensor-level defenses. The map serves as a trusted third party that validates whether detected objects are legitimate or spoofed.
Solution Approach 2:
The system performs preliminary actions by pre-storing detailed map data including static objects, road geometries, and navigation routes before the vehicle reaches those locations. This advance preparation creates a reference framework that enables rapid spoofing detection during operation without requiring complex real-time analysis algorithms.
2Measurement precision
If ADVs implement comprehensive spoofing detection mechanisms, then detection precision is improved, but processing time and computational resources increase
Solution Approach 1:
The system applies partial verification by focusing detection efforts on critical navigation elements such as static objects, road boundaries, and predefined route features rather than analyzing all sensor data comprehensively. By verifying only the most important spatial references against map data, the system achieves sufficient detection precision without exhaustive processing of all sensor inputs.
Solution Approach 2:
The detection process is segmented into distinct verification stages: comparing detected static objects against map data, verifying road geometry consistency, and validating route adherence. This segmentation allows the system to process different aspects of spoofing detection separately and efficiently, reducing overall processing time while maintaining comprehensive detection precision.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
Systems and methods are disclosed for an ADV to leverage pre-defined static objects along a planned route of travel to detect and counter attacks that attempt to change the destination or the planned route. The ADV may detect updates to the static objects if the planned route is changed. Based on the updated static objects, the ADV determines if there is an abnormal re-routing of the planned route or if there is a new route due to a suspicious destination change. The ADV may also leverage the static objects to detect spoofing attacks against the sensor system. The ADV may evaluate if sensors of the sensor system are able to detect and identify the static objects to identify an impaired sensor. The ADV may perform cross-check on the ability of the sensors to detect and identify dynamic objects to gain confidence that the impaired sensor is due to spoofing attacks.