This manuscript presents the updated version of the Neural Network Verification (NNV) tool.
NNV is a formal verification software tool for deep learning models and cyber-physical …

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an
unknown and stochastic environment under hard constraints that require the system state …

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen
driving scenarios, largely stemming from the non-interpretability and poor generalization of …

We present a novel approach to efficiently compute tight non-convex enclosures of the
image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation …

Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …

The rapid advance of deep reinforcement learning techniques enables the oversight of
safety-critical systems through the utilization of Deep Neural Networks (DNNs). This …

This report presents the results of a friendly competition for formal verification of continuous
and hybrid systems with artificial intelligence (AI) components. Specifically, machine …

Model-based reinforcement learning has been widely studied for controller synthesis in
cyber-physical systems (CPSs). In particular, for safety-critical CPSs, it is important to …

The formal verification of neural networks is essential for their application in safety-critical
environments. However, the set-based verification of neural networks using linear …

The robustness of deep neural networks has received significant interest recently, especially
when being deployed in safety-critical systems, as it is important to analyze how sensitive …