Anomaly Detection and Functional Testing for Automotive CAN Communication
Bibliographic record
Abstract
Integrated vehicle dynamics control systems require real-time communication among their components to improve performance and process efficiency. This communication relies on the use of sensor data, hardware interfaces, transmission protocols, and control strategies, which all have an impact on the system’s reliability. However, as the number of functionalized electronic control units (ECUs) and wiring systems increases, advanced control systems encounter complex functional and cybersecurity issues. To mitigate this complexity, the automotive industry widely employs the Controller Area Network (CAN) communication bus. Nevertheless, the inherent vulnerabilities of CAN and the rich interfaces with external environments increase the systems’ susceptibility to soft errors caused by uncertainty factors such as process changes. Therefore, detecting abnormalities in automotive CAN communication is crucial.This paper introduces a machine learning (ML)-based anomaly detection framework to identify anomalies through CAN messages, extracting key features and employing ML models for predictive analysis. It also uses Triple Modular Redundancy (TMR) for trusted ML computation in anomaly detection. The study provides a comparative analysis of various ML algorithms, highlighting the effectiveness of Deep Neural Networks in identifying anomalies within both synthetic and real Hyundai CAN data for a wheel speed control system, showcasing the framework’s capability to enhance system reliability and security.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".