arXiv:2401.14461v1 [cs.AI] 25 Jan 2024 Page 1 Marabou 2.0: A Versatile Formal Analyzer of
Neural Networks Haoze Wu1, Omri Isac2, Aleksandar Zeljic1, Teruhiro Tagomori1,3, Matthew …

Deep neural networks (DNNs) are the workhorses of deep learning, which constitutes the
state of the art in numerous application domains. However, DNN-based decision rules are …

Deep neural networks (DNNs) are increasingly being used as controllers in reactive
systems. However, DNNs are highly opaque, which renders it difficult to explain and justify …

Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide
variety of robotic applications. A natural consequence is the adoption of this paradigm for …

In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in
machine learning due to its successful applications to real-world and complex systems …

Deep Neural Networks are increasingly adopted in critical tasks that require a high level of
safety, eg, autonomous driving. While state-of-the-art verifiers can be employed to check …

Deep reinforcement learning (DRL) is a powerful machine learning paradigm for generating
agents that control autonomous systems. However, the" black box" nature of DRL agents …

Deep neural networks (DNNs) are increasingly being employed in safety-critical systems,
and there is an urgent need to guarantee their correctness. Consequently, the verification …

Deep neural networks (DNNs) have become the technology of choice for realizing a variety
of complex tasks. However, as highlighted by many recent studies, even an imperceptible …

Safety is essential for deploying Deep Reinforcement Learning (DRL) algorithms in real-
world scenarios. Recently, verification approaches have been proposed to allow quantifying …