Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

LLM-Empowered Functional Safety and Security by Design in Automotive Systems

Nenad Petrovic, Vahid Zolfaghari, Fengjunjie Pan, Alois Knoll

TL;DR

The paper tackles the challenge of ensuring functional safety and cybersecurity in Software Defined Vehicles by proposing an LLM-empowered, event-chain–driven workflow grounded in Model-Driven Engineering. It integrates Retrieval-Augmented Generation to ground LLM outputs to authoritative VSS/CAN catalogs and enforces safety and security constraints via formalized event chains and OCL-based rules, aligned with ISO 26262 and ISO 21434. The approach is demonstrated through ADAS-focused case studies on physical testbenches and simulators, showing diverse performance across commercial and locally deployable LLMs in CAN-FD/VSS mapping and event-chain reasoning. Overall, the work advances automated, auditable early-stage safety-security analyses for SDVs and outlines directions for broader language-model deployment and language-support extensions such as Rust.

Abstract

This paper presents LLM-empowered workflow to support Software Defined Vehicle (SDV) software development, covering the aspects of security-aware system topology design, as well as event-driven decision-making code analysis. For code analysis we adopt event chains model which provides formal foundations to systematic validation of functional safety, taking into account the semantic validity of messages exchanged between key components, including both CAN and Vehicle Signal Specification (VSS). Analysis of security aspects for topology relies on synergy with Model-Driven Engineering (MDE) approach and Object Constraint Language (OCL) rules. Both locally deployable and proprietary solution are taken into account for evaluation within Advanced Driver-Assistance Systems (ADAS)-related scenarios.

LLM-Empowered Functional Safety and Security by Design in Automotive Systems

TL;DR

The paper tackles the challenge of ensuring functional safety and cybersecurity in Software Defined Vehicles by proposing an LLM-empowered, event-chain–driven workflow grounded in Model-Driven Engineering. It integrates Retrieval-Augmented Generation to ground LLM outputs to authoritative VSS/CAN catalogs and enforces safety and security constraints via formalized event chains and OCL-based rules, aligned with ISO 26262 and ISO 21434. The approach is demonstrated through ADAS-focused case studies on physical testbenches and simulators, showing diverse performance across commercial and locally deployable LLMs in CAN-FD/VSS mapping and event-chain reasoning. Overall, the work advances automated, auditable early-stage safety-security analyses for SDVs and outlines directions for broader language-model deployment and language-support extensions such as Rust.

Abstract

This paper presents LLM-empowered workflow to support Software Defined Vehicle (SDV) software development, covering the aspects of security-aware system topology design, as well as event-driven decision-making code analysis. For code analysis we adopt event chains model which provides formal foundations to systematic validation of functional safety, taking into account the semantic validity of messages exchanged between key components, including both CAN and Vehicle Signal Specification (VSS). Analysis of security aspects for topology relies on synergy with Model-Driven Engineering (MDE) approach and Object Constraint Language (OCL) rules. Both locally deployable and proprietary solution are taken into account for evaluation within Advanced Driver-Assistance Systems (ADAS)-related scenarios.
Paper Structure (10 sections, 4 figures, 3 tables)

This paper contains 10 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background and Related Works
  3. Implementation overview
  4. Code analysis workflow
  5. Security Analysis of System Topology
  6. Case Study Overview
  7. Functional Safety Analysis
  8. Topology Analysis
  9. Experiments and Evaluation
  10. Conclusion

Figures (4)

  • Figure 1: Workflow of LLM-empowered event chain-based functional safety by design workflow for automotive.
  • Figure 2: LLM-driven topology-level security by design workflow.
  • Figure 3: Overview of functional safety scenarios in activity diagram notation.
  • Figure 4: Metamodel behind the security-aware topology analysis case study.