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

TL;DR

This paper introduces an LLM-empowered workflow for enhancing functional safety and security in automotive software development, integrating formal validation, system topology analysis, and event-driven decision-making.

Contribution

It proposes a novel LLM-based approach combining formal methods, MDE, and OCL for security-aware design and safety validation in automotive systems.

Findings

Effective validation of message semantics in CAN and VSS

Integration of LLM with formal safety analysis methods

Evaluation within ADAS scenarios shows promising results

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.