No abstract

Neural State Classification (NSC) is a recently proposed method for runtime predictive monitoring of Hybrid Automata (HA) using deep neural networks (DNNs). NSC trains a DNN as an approximate reachability predictor that labels a given HA state x as positive if an unsafe state is reachable from x within a given time bound, and labels x as negative otherwise. NSC predictors have very high accuracy, yet are prone to prediction errors that can negatively impact reliability. To overcome this limitation, we present Neural Predictive Monitoring (NPM), a technique based on NSC and conformal prediction that complements NSC predictions with statistically sound estimates of uncertainty. This yields principled criteria for the rejection of predictions likely to be incorrect, without knowing the true reachability values. We also present an active learning method that significantly reduces both the NSC predictor's error rate and the percentage of rejected predictions. Our approach is highly efficient, with computation times on the order of milliseconds, and effective, managing in our experimental evaluation to successfully reject almost all incorrect predictions.

Neural state classification (NSC) is a recently proposed method for runtime predictive monitoring of hybrid automata (HA) using deep neural networks (DNNs). NSC trains a DNN as an approximate reachability predictor that labels an HA state x as positive if an unsafe state is reachable from x within a given time bound, and labels x as negative otherwise. NSC predictors have very high accuracy, yet are prone to prediction errors that can negatively impact reliability. To overcome this limitation, we present neural predictive monitoring (NPM), a technique that complements NSC predictions with estimates of the predictive uncertainty. These measures yield principled criteria for the rejection of predictions likely to be incorrect, without knowing the true reachability values. We also present an active learning method that significantly reduces the NSC predictor’s error rate and the percentage of rejected predictions. We develop two versions of NPM based, respectively, on the use of frequentist and Bayesian techniques to learn the predictor and the rejection rule. Both versions are highly efficient, with computation times on the order of milliseconds, and effective, managing in our experimental evaluation to successfully reject almost all incorrect predictions. In our experiments on a benchmark suite of six hybrid systems, we found that the frequentist approach consistently outperforms the Bayesian one. We also observed that the Bayesian approach is less practical, requiring a careful and problem-specific choice of hyperparameters.

No abstract

Neural State Classification (NSC) [19] is a scalable method for the analysis of hybrid systems, which consists in learning a neural network-based classifier able to detect whether or not an unsafe state can be reached from a certain configuration of a hybrid system. NSC has very high accuracy, yet it is prone to prediction errors that can affect system safety. To overcome this limitation, we present a method, based on the theory of conformal prediction, that complements NSC predictions with statistically sound estimates of prediction uncertainty. This results in a principled criterion to reject potentially erroneous predictions a priori, i.e., without knowing the true reachability values. Our approach is highly efficient (with runtimes in the order of milliseconds) and effective, managing in our experiments to successfully reject almost all the wrong NSC predictions.