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

2026-01-05

arXiv.org

AI Summary

This work proposes a large language model (LLM)-driven co-verification workflow to address the challenges of co-designing functional safety and cybersecurity in software-defined vehicles, particularly the difficulties in ensuring semantic consistency and regulatory compliance during system topology construction and event-driven code analysis. By integrating model-driven engineering, event chain modeling, Object Constraint Language (OCL), and CAN/VSS semantic specifications, the approach achieves the first automated LLM-enabled joint safety-security verification for automotive systems. Experimental evaluation in an ADAS scenario demonstrates that the proposed solution supports on-premise deployment and significantly improves the efficiency of verifying both system topology safety and the functional safety of code-level decision logic.

Technology Category

• Natural Language Processing: Safety and Robustness
• Machine Learning: Large Multimodal Models (LMMs)
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Large-scale security measurements

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.

Problem

• Functional Safety
• Cybersecurity
• Software Defined Vehicle
• Event-driven Code Analysis
• System Topology Design

Innovation

• LLM-empowered workflow
• event chains model
• Model-Driven Engineering
• functional safety
• security-aware topology