The vulnerability of deep neural networks (DNNs) to input perturbations has posed a
significant challenge. Recent work on robustness verification of DNNs not only lacks …

Verification plays an essential role in the formal analysis of safety-critical systems. Most
current verification methods have specific requirements when working on Deep Neural …

When using deep neural networks to operate safety-critical systems, assessing the
sensitivity of the network outputs when subject to uncertain inputs is of paramount …

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic
reachability problem for feed-forward DNNs which, for a given set of inputs to the network …

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 introduce ReachNN*, a tool for reachability analysis of neural-network controlled
systems (NNCSs). The theoretical foundation of ReachNN* is the use of Bernstein …

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

With the applications of deep learning in safety-critical domains such as autonomous driving
systems gaining ground, it demands rigorous verification to guarantee the safety and …

Deep neural networks (DNNs) have been shown lack of robustness, as they are vulnerable
to small perturbations on the inputs. This has led to safety concerns on applying DNNs to …

Abstract Recurrent Neural Networks (RNNs) are one of the most successful neural network
architectures that deal with temporal sequences, eg, speech and text recognition. Recently …