Carpenter, Taylor J.Ivanov, RadoslavLee, InsupWeimer, James2023-05-222023-05-222021-07-012021-08-19https://repository.upenn.edu/handle/20.500.14332/6954This paper presents ModelGuard, a sampling-based approach to runtime model validation for Lipschitz-continuous models. Although techniques exist for the validation of many classes of models, the majority of these methods cannot be applied to the whole of Lipschitz-continuous models, which includes neural network models. Additionally, existing techniques generally consider only white-box models. By taking a sampling-based approach, we can address black-box models, represented only by an input-output relationship and a Lipschitz constant. We show that by randomly sampling from a parameter space and evaluating the model, it is possible to guarantee the correctness of traces labeled consistent and provide a confidence on the correctness of traces labeled inconsistent. We evaluate the applicability and scalability of ModelGuard in three case studies, including a physical platform.CPS Safe Autonomymodel invalidationneural networkcomputational toolmonitoringComputer EngineeringComputer SciencesPresentation