Cyber-physical systems (CPSs) are now widely deployed in many industrial domains, e.g., manufacturing systems and autonomous vehicles. To further enhance the capability and applicability of CPSs, there comes a recent trend from both academia and industry to utilize learning-based AI controllers for the system control process, resulting in an emerging class of AI-enabled cyber-physical systems (AI-CPSs). Although such AI-CPSs could achieve obvious performance enhancement from the lens of some key industrial requirement indicators, due to the random exploration nature and lack of systematic explanations for their behavior, such AI-based techniques also bring uncertainties and safety risks to the controlled system, posing an urgent need for effective safety analysis techniques for AI-CPSs. Hence in this work, we propose Mosaic, a model-based safety analysis framework for AI-CPSs. Mosaic first constructs a Markov decision process (MDP) model as an abstract model of the AI-CPS, which tries to characterize the behaviors of the original AI-CPS. Then, based on the derived abstract model, safety analysis is designed in two aspects: online safety monitoring and offline model-guided falsification. The usefulness of Mosaic is evaluated on diverse and representative industry-level AI-CPSs, the results of which demonstrate that Mosaic is effective in providing safety monitoring to AI-CPSs and enables to outperform the state-of-the-art falsification techniques, providing the basis for advanced safety analysis of AI-CPSs.

翻译：信息物理系统（CPS）现已广泛应用于制造系统、自动驾驶车辆等多个工业领域。为进一步提升CPS的能力和适用性，学术界与工业界近期出现利用基于学习的AI控制器进行系统控制过程的趋势，由此催生了新兴的人工智能赋能信息物理系统（AI-CPS）。尽管从关键工业需求指标来看，此类AI-CPS能实现显著的性能提升，但由于其随机探索特性及缺乏系统化的行为解释，基于AI的技术也给受控系统带来了不确定性和安全风险，亟需针对AI-CPS的有效安全性分析技术。为此，本文提出Mosaic——面向AI-CPS的基于模型的安全性分析框架。Mosaic首先构建马尔可夫决策过程（MDP）模型作为AI-CPS的抽象模型，旨在表征原始AI-CPS的行为特征；随后基于导出的抽象模型，从在线安全监测与离线模型引导的虚假性验证两个维度设计安全性分析。通过在多样化且具有代表性的工业级AI-CPS上进行评估，结果表明Mosaic能有效为AI-CPS提供安全监测，并在性能上超越当前最先进的虚假性验证技术，为AI-CPS的进阶安全性分析奠定基础。