Related papers: Neural Network Verification is a Programming Langu…

Many approaches for verifying input-output properties of neural networks have been proposed recently. However, existing algorithms do not scale well to large networks. Recent work in the field of model compression studied binarized neural…

We investigate the computational complexity of neural network verification in quantised settings. We distinguish three classes of Feedforward Neural Networks (FNNs): rational FNNs with exact rational weights, quantised FNNs whose weights…

The networking field is characterized by its high complexity and rapid iteration, requiring extensive expertise to accomplish network tasks, ranging from network design, configuration, diagnosis and security. The inherent complexity of…

Local robustness verification can verify that a neural network is robust wrt. any perturbation to a specific input within a certain distance. We call this distance Robustness Radius. We observe that the robustness radii of correctly…

In theory, a neural network can be trained to act as an artificial specification for a program by showing it samples of the programs executions. In practice, the training turns out to be very hard. Programs often operate on discrete domains…

Enabling a machine to read and comprehend the natural language documents so that it can answer some questions remains an elusive challenge. In recent years, the popularity of deep learning and the establishment of large-scale datasets have…

In this paper, we consider the computational complexity of formally verifying the behavior of Rectified Linear Unit (ReLU) Neural Networks (NNs), where verification entails determining whether the NN satisfies convex polytopic…

Nowadays, we are witnessing a wide adoption of Machine learning (ML) models in many safety-critical systems, thanks to recent breakthroughs in deep learning and reinforcement learning. Many people are now interacting with systems based on…

In recent years, there has been considerable innovation in the world of predictive methodologies. This is evident by the relative domination of machine learning approaches in various classification competitions. While these algorithms have…

Verification and validation of vehicles is a complex yet critical process, particularly for ensuring safety and coverage through simulations. However, achieving realistic and useful simulations comes with significant challenges. To explore…

Static analysis is one of the most widely adopted techniques to find software bugs before code is put in production. Designing and implementing effective and efficient static analyses is difficult and requires high expertise, which results…

We investigate the computational complexity of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with…

Natural language processing for programming aims to use NLP techniques to assist programming. It is increasingly prevalent for its effectiveness in improving productivity. Distinct from natural language, a programming language is highly…

Barrier certificates play an important role in verifying the safety of continuous-time systems, including autonomous driving, robotic manipulators and other critical applications. Recently, ReLU neural barrier certificates -- barrier…

[Context and motivation] When developing software, coordination between different organizational units is essential in order to develop a good quality product, on time and within budget. Particularly, the synchronization between…

Safety-critical systems with neural network components require strong guarantees. While existing neural network verification techniques have shown great progress towards this goal, they cannot prove the absence of software faults in the…

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 notoriously prone to poor generalization, i.e., may prove…

Neural networks currently dominate the machine learning community and they do so for good reasons. Their accuracy on complex tasks such as image classification is unrivaled at the moment and with recent improvements they are reasonably easy…

When validated neural networks (NNs) are pruned (and retrained) before deployment, it is desirable to prove that the new NN behaves equivalently to the (original) reference NN. To this end, our paper revisits the idea of differential…

Advances in machine learning (ML) open the way to innovating functions in the avionic domain, such as navigation/surveillance assistance (e.g. vision-based navigation, obstacle sensing, virtual sensing), speechto-text applications,…