2017/12/05 by Dung Phan, Phan, Dung, Radu Grosu +7
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Formal Methods in Verification #Machine Learning (cs.LG) #Software Reliability and Analysis Research
paper · pdf · doi:10.48550/arxiv.1712.01935
openalex publication_date 2017/12/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We show how machine-learning techniques, particularly neural networks, offer a very effective and highly efficient solution to the approximate model-checking problem for continuous and hybrid systems, a solution where the general-purpose model checker is replaced by a model-specific classifier trained by sampling model trajectories. To the best of our knowledge, we are the first to establish this link from machine learning to model checking. Our method comprises a pipeline of analysis techniques for estimating and obtaining statistical guarantees on the classifier's prediction performance, as well as tuning techniques to improve such performance. Our experimental evaluation considers the time-bounded reachability problem for three well-established benchmarks in the hybrid systems community. On these examples, we achieve an accuracy of 99.82% to 100% and a false-negative rate (incorrectly predicting that unsafe states are not reachable from a given state) of 0.0007 to 0. We believe that this level of accuracy is acceptable in many practical applications and we show how the approximate model checker can be made more conservative by tuning the classifier through further training and selection of the classification threshold.