DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems

TL;DR

DURA-CPS is a framework that uses multi-role agents to automate dependability assurance in AI-enabled cyber-physical systems, improving vulnerability detection and recovery in safety-critical applications.

Contribution

It introduces a multi-role orchestration framework for continuous assurance of AI components in CPS, addressing verification challenges in dynamic environments.

Findings

Effective detection of vulnerabilities in autonomous vehicle scenarios

Supports adaptive recovery strategies for AI components

Enhances dependability assurance through continuous evaluation

Abstract

Cyber-Physical Systems (CPS) increasingly depend on advanced AI techniques to operate in critical applications. However, traditional verification and validation methods often struggle to handle the unpredictable and dynamic nature of AI components. In this paper, we introduce DURA-CPS, a novel framework that employs multi-role orchestration to automate the iterative assurance process for AI-powered CPS. By assigning specialized roles (e.g., safety monitoring, security assessment, fault injection, and recovery planning) to dedicated agents within a simulated environment, DURA-CPS continuously evaluates and refines AI behavior against a range of dependability requirements. We demonstrate the framework through a case study involving an autonomous vehicle navigating an intersection with an AI-based planner. Our results show that DURA-CPS effectively detects vulnerabilities, manages performance impacts, and supports adaptive recovery strategies, thereby offering a structured and extensible solution for rigorous V&V in safety- and security-critical systems.