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 …

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 …

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 …

Abstract Neural Networks (NNs) have increasingly apparent safety implications
commensurate with their proliferation in real-world applications: both unanticipated as well …

Machine learning techniques often lack formal correctness guarantees. This is evidenced by
the widespread adversarial examples that plague most deep-learning applications. This …

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 …

We present the first automated verification technique for confidence-based 2-safety
properties, such as global robustness and global fairness, in deep neural networks (DNNs) …

The increasing use of deep neural networks for safety-critical applications, such as
autonomous driving and flight control, raises concerns about their safety and reliability …

Machine learning techniques often lack formal correctness guarantees, evidenced by the
widespread adversarial examples that plague most deep-learning applications. This lack of …

The intrinsic complexity of deep neural networks (DNNs) makes it challenging to verify not
only the networks themselves but also the hosting DNN-controlled systems. Reachability …