Explainable AI for Intrusion Detection Systems in Automotive
Reference number | |
Coordinator | RISE Research Institutes of Sweden AB |
Funding from Vinnova | SEK 100 000 |
Project duration | January 2025 - June 2025 |
Status | Ongoing |
Venture | 6G - Competence supply |
Call | 6G - Supervision of degree work |
Important results from the project
The project developed an explainable intrusion detection solution for Automotive Ethernet using Logical Neural Networks (LNN), demonstrating both high accuracy and interpretability. The project goals were fully achieved.
Expected long term effects
The solution can help make future massively connected vehicle networks more secure and transparent by promoting the use of explainable AI in safety-critical applications.
Approach and implementation
The project was carried out in four stages: data preparation, AI model training, development of explainability methods (SHAP, LNN), and performance evaluation. Collaboration between academia and industry worked well, and the project stayed on schedule.