From Challenges to Opportunities: A Comprehensive Study of AI-based In-Vehicle Intrusion Detection Systems
Résumé
While significant research has been conducted on
ML-based In-Vehicle Intrusion Detection Systems (IV-IDS), the
practical application of these systems needs further refinement.
The safety-critical nature of IV-IDS calls for precise and objective
evaluation and feasibility assessment metrics. This paper
responds to this need by conducting a rigorous ML-based IVIDS
analysis. We offer a thorough review of recent automotive
forensics studies spotlighting the constraints relevant to Invehicles
networks and the associated security/safety requirements
to reveal the current gaps in the existing literature. By addressing
the limitations of AI in IV-IDS, this paper contributes to the
existing research corpus and defines pertinent baseline metrics
for in-vehicle networked systems. Essentially, we reconcile the
requirements of real-world autonomous vehicles with those of
the security domain, enabling an assessment of the viability of
AI-based intrusion detection systems.
Origine | Fichiers produits par l'(les) auteur(s) |
---|---|
Licence |