Anomaly Detection Server for Vehicle On-Board Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for detecting and defending against attack frames in vehicle on-board networks are limited in their ability to detect a variety of attack frames, particularly those that cannot be discriminated using pre-registered anticipated periods.
Innovation Solution
A security processing method that assesses the anomaly level of frames received on an on-board network by acquiring information about multiple frames and applying statistical processing, multivariate analysis, and machine learning to identify anomalies that may not be detected by traditional fraud detection techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If pre-registered anticipated periods are used to detect attack frames, then detection simplicity is improved, but detection coverage deteriorates (cannot detect variety of attack frames)
Solution Approach 1:
The patent changes the detection parameters from fixed pre-registered anticipated periods to dynamically calculated statistical parameters (mean, standard deviation) derived from multiple vehicles' frame reception data. This allows the system to adapt to different attack patterns while maintaining automated operation.
Solution Approach 2:
The patent creates a universal detection mechanism that collects frame reception information from multiple vehicles and uses statistical processing to generate detection thresholds applicable to various attack types. This multi-functional approach enables the system to detect different varieties of attack frames using a single unified method.
2Measurement precision
If statistical processing and machine learning are applied to assess anomaly levels, then detection accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the computational workload by dividing frame reception information from multiple vehicles into separate datasets, processing each vehicle's data independently to calculate statistical parameters. This segmentation reduces the complexity of handling large aggregated datasets while maintaining detection accuracy through comparative analysis.
Solution Approach 2:
The patent introduces statistical parameters (mean, standard deviation) as intermediary values that simplify the complex task of anomaly detection. Instead of directly analyzing raw frame reception data from multiple vehicles, the system uses these statistical intermediaries to assess anomaly levels, reducing computational complexity while preserving detection precision.
3Reliability
If information from multiple vehicles is collected and processed, then anomaly detection capability is improved, but communication and processing load increases
Solution Approach 1:
The patent extracts only the necessary frame reception information (timing, message ID, counter values) from multiple vehicles without transmitting or processing complete frame data. This extraction approach maintains reliable anomaly detection capability by focusing on critical temporal and identification parameters while significantly reducing communication and processing loads.
Data Source
AI summary
An anomaly detection server is provided. The anomaly detection server is a server for counteracting an anomalous frame transmitted on an on-board network of a single vehicle. The anomaly detection server acquires information about multiple frames received on one or multiple on-board networks of one or multiple vehicles, including the single vehicle. The anomaly detection server, acting as an assessment unit that, based on the information about the multiple frames and information about a frame received on the on-board network of the single vehicle after the acquisition of the information about the multiple frames, assesses an anomaly level of the frame received on the on-board network of the single vehicle.