DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems
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.
View on arXiv@article{srinivasan2025_2506.06381,
title={ DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems },
author={ Trisanth Srinivasan and Santosh Patapati and Himani Musku and Idhant Gode and Aditya Arora and Samvit Bhattacharya and Abubakr Nazriev and Sanika Hirave and Zaryab Kanjiani and Srinjoy Ghose },
journal={arXiv preprint arXiv:2506.06381},
year={ 2025 }
}