Causal Graph Sensing Data Correction for Tamper Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems are vulnerable to malicious attacks and data tampering, which can lead to dangerous misinterpretations of road signs and lane markers, causing vehicles to deviate from their intended paths.
Innovation Solution
A data correction method and computing apparatus for machine learning that relates multiple pieces of sensing data to generate causal relationships, compares these relationships with reference causal relationships, and modifies the data to align with correct causal graphs, using machine learning models to ensure accurate data integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensing data sources are integrated to improve detection accuracy, then the system becomes more vulnerable to coordinated attacks and data tampering, but security and reliability deteriorate
Solution Approach 1:
The patent introduces a causal graph as an intermediary representation that models the causal relationships between different sensing data sources. This causal graph serves as a mediator that allows the system to integrate multiple sensing inputs while maintaining the ability to detect inconsistencies and tampering, thus resolving the contradiction between improved detection accuracy through multi-source integration and system security against coordinated attacks.
2Adaptability or versatility
If the system accepts all sensing data from multiple sources to improve comprehensive detection, then erroneous or tampered data can cause dangerous misinterpretations, but safety deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where the causal graph continuously monitors and validates the consistency of sensing data from multiple sources. When inconsistencies or tampering are detected through causal relationship analysis, the system provides feedback to correct or reject erroneous data, thereby maintaining comprehensive detection capability while preventing safety risks from misinterpretation of tampered data.
Data Source
AI summary
A data correction method, a computing apparatus used for machine learning, and a computer-readable medium are provided. In the method, multiple pieces of sensing data are related, and a causal relationship is generated. The causal relationship is compared, and a comparison result is generated. The comparison result is used for modifying the sensing data. The machine learning model is trained through inputting the modified sensing data. Therefore, the correctness of data can be ensured.