The paper extends the recent star reachability method to verify the robustness of recurrent
neural networks (RNNs) for use in safety-critical applications. RNNs are a popular machine …

This paper presents a property-directed approach to verifying recurrent neural networks
(RNNs). To this end, we learn a deterministic finite automaton as a surrogate model from a …

Deep neural networks are increasingly being used as controllers for safety-critical systems.
Because neural networks are opaque, certifying their correctness is a significant challenge …

Deep Neural Networks (DNNs) have become a popular instrument for solving various real-
world problems. DNNs' sophisticated structure allows them to learn complex representations …

Deep neural networks have achieved impressive results in many complex applications,
including classification tasks for image and speech recognition, pattern analysis or …

Neural networks are increasingly applied to support decision making in safety-critical
applications (like autonomous cars, unmanned aerial vehicles and face recognition based …

Certifiable robustness, the functionality of verifying whether the given region surrounding a
data point admits any adversarial example, provides guaranteed security for neural …

Neural network controllers (NNCs) have shown great promise in autonomous and cyber-
physical systems. Despite the various verification approaches for neural networks, the safety …

We study the verification problem for closed-loop dynamical systems with neural-network
controllers (NNCS). This problem is commonly reduced to computing the set of reachable …

Most work on the formal verification of neural networks has focused on bounding the set of
outputs that correspond to a given set of inputs (for example, bounded perturbations of a …