Vehicle Trajectory Deviation Detection for Compromise Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern vehicles with increased connectivity and automated driving systems are vulnerable to compromise by malicious third parties, which can control vehicle systems without the driver's knowledge, making detection and response to such compromises challenging.
Innovation Solution
A method and system that analyze monitored vehicle inputs, predict and compare vehicle trajectories, and generate response actions when deviation thresholds are exceeded, including security sweeps, alerts, and system shut-offs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If vehicle connectivity and automated driving systems are increased, then vehicle functionality and convenience are improved, but vulnerability to compromise by malicious third parties increases
Solution Approach 1:
The system performs preliminary actions by continuously monitoring vehicle inputs and predicting expected trajectories before compromise can occur. The baseline trajectory is established in advance, allowing the system to detect deviations that indicate malicious control attempts before they can cause harm.
Solution Approach 2:
The system implements feedback by continuously comparing actual vehicle trajectory against predicted baseline trajectory, detecting deviations that indicate compromise, and triggering appropriate responses. This closed-loop feedback mechanism enables real-time detection and response to security threats.
2Reliability
If traditional security measures are implemented, then protection against compromise is improved, but detection capability against concealed compromise deteriorates
Solution Approach 1:
The system uses trajectory prediction as an intermediary mechanism to detect compromise. Rather than directly monitoring for malicious control signals, the system compares actual vehicle behavior against predicted baseline behavior, allowing indirect detection of concealed compromise through behavioral anomalies.
Solution Approach 2:
The system replaces traditional mechanical security measures with a software-based behavioral analysis system. Instead of relying on hardware security modules or authentication protocols, the system uses computational prediction and comparison of vehicle trajectory data to detect compromise.
3Measurement precision
If real-time trajectory monitoring and analysis are implemented, then detection accuracy is improved, but computational resource requirements and system complexity increase
Solution Approach 1:
The system extracts only the essential features needed for trajectory prediction and comparison, focusing on key input parameters and trajectory characteristics. This selective extraction reduces computational complexity while maintaining detection accuracy by concentrating on the most relevant data elements.
Solution Approach 2:
The system changes parameters by transforming raw vehicle input data into predicted trajectory parameters, then comparing these transformed parameters against actual trajectory measurements. This parameter transformation enables efficient computation while preserving the ability to detect deviations.
4Reliability
If response actions are generated when trajectory deviation exceeds threshold, then response effectiveness is improved, but false positive rate may increase
Solution Approach 1:
The system applies preliminary anti-action by establishing a baseline trajectory that accounts for normal variations in vehicle behavior. This baseline serves as a pre-computed reference that reduces false positives by distinguishing between normal deviations and actual compromise indicators.
Data Source
AI summary
A method for detecting and responding to the detection of a compromised vehicle comprises: receiving one or more monitored inputs of a vehicle; predicting, using at least one of the monitored inputs, a predicted vehicle trajectory; detecting a detected vehicle trajectory; comparing the predicted vehicle trajectory to the detected vehicle trajectory; determining a trajectory deviation value of the predicted vehicle trajectory and the detected vehicle trajectory; in response to determining that the trajectory deviation value exceeds a pre-determined trajectory deviation threshold, generating a response action; and implementing the response action.


