Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.06381 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913890731819008 |
|---|---|
| author | Srinivasan, Trisanth Patapati, Santosh Musku, Himani Gode, Idhant Arora, Aditya Bhattacharya, Samvit Nazriev, Abubakr Hirave, Sanika Kanjiani, Zaryab Ghose, Srinjoy |
| author_facet | Srinivasan, Trisanth Patapati, Santosh Musku, Himani Gode, Idhant Arora, Aditya Bhattacharya, Samvit Nazriev, Abubakr Hirave, Sanika Kanjiani, Zaryab Ghose, Srinjoy |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06381 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems Srinivasan, Trisanth Patapati, Santosh Musku, Himani Gode, Idhant Arora, Aditya Bhattacharya, Samvit Nazriev, Abubakr Hirave, Sanika Kanjiani, Zaryab Ghose, Srinjoy Robotics Artificial Intelligence Emerging Technologies Human-Computer Interaction Multiagent Systems C.3; C.4; D.2.4; D.4.6; I.2.7 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. |
| title | DURA-CPS: A Multi-Role Orchestrator for Dependability Assurance in LLM-Enabled Cyber-Physical Systems |
| topic | Robotics Artificial Intelligence Emerging Technologies Human-Computer Interaction Multiagent Systems C.3; C.4; D.2.4; D.4.6; I.2.7 |
| url | https://arxiv.org/abs/2506.06381 |