Sensor and Decision Fusion-Based Intrusion Detection and Mitigation Approach for Connected Autonomous Vehicles
Bibliographic record
Abstract
The safety of Connected and Autonomous Vehicle (CAV) depends on the security of in-vehicle communication. The Controller Area Network (CAN) bus holds a crucial position in ensuring in-vehicle security. Injecting attacks (e.g., increasing the speed) by hackers can affect drivers. This article proposes a fusion intrusion detection and resilient approach to maintain system performance against intrusion. The proposed system consists of two parts: sensor validation and sensor value estimation. In the sensor validation step, a new fusion approach using three feature ranking approaches, auto-encoder and estimator-based detectors. Finally, Yager’s rules are employed to handle conflict between classifiers and enrich intrusion detection accuracy. Afterward, in the second part, if any intrusion is detected, the estimated values of that sensor which is under intrusion will be replaced based on estimated values by Long-Short Term Memory-based Deep Regressor (LSTMDR) to avoid any performance disruption of the system. The main contribution of this study is that the proposed fusion approach utilizes the inherent redundancy among heterogeneous sensors to create a resilient system against compromised sensors. Utilizing Yager’s rule and the Ordered Weighted Average for information fusion significantly increases the reliability of intrusion detection systems and improves their detection rates. It also improves the performance of soft sensors and enhances the effectiveness of the mitigation phase. To evaluate the proposed approach, a real-world dataset entitled AEGIS - Advanced Big Data Value Chain for Public Safety and Personal Security is used. Test results indicate that the proposed fusion method is robust and reaches more accurate results compared to other detectors in three different considered attacks including replay, Denial of Service, and False Data Injection.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".