Deep neural networks are widely used for nonlinear function approximation, with
applications ranging from computer vision to control. Although these networks involve the …

Neural networks as a machine learning technique are increasingly deployed in various
domains. Despite their performance and their continuous improvement, the deployment of …

This paper proposes novel reachability algorithms for both exact (sound and complete) and
over-approximation (sound) analysis of deep neural networks (DNNs). The approach uses …

We propose a novel, complete algorithm for the verification and analysis of feed-forward,
ReLU-based neural networks. The algorithm, based on symbolic interval propagation …

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 …

With the rapid growth of machine learning, deep neural networks (DNNs) are now being
used in numerous domains. Unfortunately, DNNs are “black-boxes”, and cannot be …

We propose a novel verification method for high-dimensional feed-forward neural networks
governed by ReLU, Sigmoid and Tanh activation functions. We show that the method is …

Robustness verification that aims to formally certify the prediction behavior of neural
networks has become an important tool for understanding model behavior and obtaining …

The application of deep reinforcement learning (DRL) to computer and networked systems
has recently gained significant popularity. However, the obscurity of decisions by DRL …

We develop a novel model for studying agent-environment systems, where the agents are
implemented via feed-forward ReLU neural networks. We provide a semantics and develop …