In-Vehicle Network Anomaly Detection with Segmented Rule Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing anomaly detecting device for in-vehicle networks lacks accuracy in rule-based anomaly detection, as it relies solely on individual or integrated rules without considering the specific characteristics of the vehicle or its environment.
Innovation Solution
An information processing device that combines individual and integrated rule storage, allowing for selective use of rules based on detection targets and environmental conditions, with the ability to invalidate or alert on detected anomalies, and includes a history storage for rule rollback when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only individual rules are used for anomaly detection, then the detection can be performed quickly, but the accuracy is insufficient because it does not consider vehicle-specific characteristics
Solution Approach 1:
The rule storage is segmented into two distinct parts: individual rule storage for vehicle-specific characteristics and integrated rule storage for common anomaly patterns. This segmentation allows the system to use appropriate rules based on the detection target, improving accuracy while managing complexity through organized storage structures.
Solution Approach 2:
The system adds a new dimension to rule storage by creating both individual (vehicle-specific) and integrated (common) rule storages. This dimensional expansion allows selective application of rules based on whether the anomaly is vehicle-specific or common across multiple vehicles, thereby improving detection accuracy without overwhelming complexity.
2Adaptability or versatility
If only integrated rules are used for anomaly detection, then the system can handle common anomalies across multiple vehicles, but it cannot detect vehicle-specific anomalies accurately
Solution Approach 1:
The rule storage is segmented into two distinct parts: individual rule storage for vehicle-specific characteristics and integrated rule storage for common anomaly patterns. This segmentation allows the system to use appropriate rules based on the detection target, improving accuracy while managing complexity through organized storage structures.
Solution Approach 2:
Different parts of the rule storage system serve different purposes: individual rules provide localized, vehicle-specific detection capabilities while integrated rules provide generalized anomaly detection. This local quality differentiation ensures that each type of rule is optimized for its specific function, enhancing both adaptability and precision.
3Measurement precision
If the system uses multiple rule storages (individual and integrated), then the detection accuracy improves, but the system complexity increases
Solution Approach 1:
The rule storage is segmented into two distinct parts: individual rule storage for vehicle-specific characteristics and integrated rule storage for common anomaly patterns. This segmentation allows the system to use appropriate rules based on the detection target, improving accuracy while managing complexity through organized storage structures.
Solution Approach 2:
The dual rule storage system serves multiple functions: individual rules handle vehicle-specific anomalies, integrated rules handle common anomalies, and the system can selectively apply either or both types of rules based on the detection needs. This multi-functionality justifies the increased complexity by providing comprehensive anomaly detection capabilities.
4Reliability
If the system stores and manages multiple types of rules, then more comprehensive anomaly detection is possible, but the ease of operation and maintenance decreases
Solution Approach 1:
The rule storage is segmented into two distinct parts: individual rule storage for vehicle-specific characteristics and integrated rule storage for common anomaly patterns. This segmentation allows the system to use appropriate rules based on the detection target, improving accuracy while managing complexity through organized storage structures.
Data Source
AI summary
An information processing device that detects an anomaly in an in-vehicle network provided in a vehicle includes: a local rule storage in which at least an individual rule which is a rule generated for the vehicle is stored; a global rule storage in which an integrated rule which is a rule generated for a plurality of vehicles including the vehicle is stored; and a processing unit that performs, using a rule stored in at least one of the local rule storage or the global rule storage, an anomaly detection process on a frame transmitted on the in-vehicle network.