Safeguarding Smart Vehicles: GNN-Powered Real- Time IDS for CAN Networks
Bibliographic record
Abstract
With the increasing integration of Controller Area Network (CAN) in modern vehicles, securing the communication network from malicious attacks is imperative. A novel Graph Neural Network (GNN)-based Intrusion Detection System (IDS) is proposed for real-time detection of several attacks, such as Denial of Service (DOS), fuzzy, and spoofing attacks. Our proposed model represents the CAN network as a graph, where nodes correspond to message arbitration ID and edges denote the communication sequence. Using Graph Attention Networks (GAT), our model captures the intricate relationships and dependencies between Electronic Circuit Units (ECUs), in real-time, enhancing its ability to discern normal behavior from malicious activity. The key to our system's success is its emphasis on achieving real-time capabilities. The GAT architecture optimizes computational efficiency for swift analysis of CAN traffic without compromising detection accuracy. Our system minimizes model complexity for enhanced deployability in resource-constrained vehicular environments. Comprehensive experiments on a diverse dataset showcase its ability to swiftly and accurately detect a range of attacks in real-time, with an overall accuracy of 99.75% for DOS attacks, 99.50% for fuzzy attacks, and 100% for spoofing attacks. Moreover, attack detection time is calculated to be 6.76 ms for DOS, 6.79 ms for fuzzy, and 6.69 ms for spoofing. These results made the model meet real-time detection constraints.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| 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".