Back to all available

AI-driven behavioral analytics for enhancing zero-trust network access in the automotive sector

artificial-intelligence
computer-architecture
computer-networks-and-communications

Abstract

Background. Connected and Autonomous Vehicles (CAVs) are becoming like cyber-physical systems defined through software with dense Vehicle-to-Everything (V2X) communications. The network perimeter is blurred, along with legacy in-vehicle buses like Controller Area Network (CAN. Unified internal and external attack vectors are correlated as a result.

Methods. It was maped threats across in-vehicle network and V2X domains, an analytic conceptual methodology applies, and formalize the observe interpret decide act loop, and metrics are defined in two categories: security effectiveness (detection rate, false positive rate, F1-score, mean time to detect, containment ratio) and operational viability (policy enforcement latency, CPU/memory load on Electronic Control Units, ECUs, network overhead, impact on real-time deadlines).

Results. It was proposed a multi-layer ZTNA architecture with UEBA tailored toward the automotive sector: (1) a layer that collects telemetry from CAN/Automotive Ethernet, V2X messages as well as sensors, and ECU diagnostics; (2) an AI-based UEBA core that builds behavioral profiles of entities, updates them, along with detects anomalies; (3) an engine that converts anomalies plus context into continuous real-time trust scores for each entity and request; (4) a mechanism and enforcement points that enable granular actions, from step-up authentication and privilege reduction until microsegmented isolation and notifications to the Vehicle Security Operations Center (VSOC). Such a loop detects zero-day and insider scenarios so early, restricts lateral movement, and enforces target policy with millisecond latency, as demonstrated now.

Conclusions. UEBA powered via AI integrates into the Zero-Trust Architecture model. This integration does shift static rules into verification that is continuous inside car networks. The measurable implementation path comes as a result of interaction with the VSOC, along with explicit key indicators. This path preserves computational resource constraints. Some directions researchers can take are robustness against adversarial manipulation, AI that is explainable for audit and certification, learning that preserves privacy, plus model management that is scalable over-the-air (OTA).

Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].