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 …
D Gopinath, G Katz, CS Păsăreanu… - Automated Technology for …, 2018 - Springer
Deep neural networks have achieved impressive results in many complex applications, including classification tasks for image and speech recognition, pattern analysis or …
G Dong, J Sun, J Wang, X Wang, T Dai - arXiv preprint arXiv:2012.01872, 2020 - arxiv.org
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 …
C Zhang, W Ruan, P Xu - Proceedings of the AAAI Conference on …, 2023 - ojs.aaai.org
Neural network controllers (NNCs) have shown great promise in autonomous and cyber- physical systems. Despite the various verification approaches for neural networks, the safety …
C Schilling, M Forets, S Guadalupe - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
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 …