DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems
This addresses the problem of ensuring safety and security in AI-enabled critical systems, offering a structured solution for developers and engineers, though it appears incremental as it builds on existing assurance methods.
The paper tackles the challenge of verifying and validating AI components in cyber-physical systems by introducing DURA-CPS, a framework that uses multi-role orchestration to automate dependability assurance, and demonstrates its effectiveness in a case study with an autonomous vehicle.
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.