In this brief, the output reachable estimation and safety verification problems for multilayer
perceptron (MLP) neural networks are addressed. First, a conception called maximum …

Reachability analysis is a fundamental problem in verification that checks for a given model
and set of initial states if the system will reach a given set of unsafe states. Its importance lies …

We present an approach to construct reachable set overapproximations for continuous-time
dynamical systems controlled using neural network feedback systems. Feedforward deep …

The surge of interest in applications of deep neural networks has led to a surge of interest in
verification methods for such architectures. In summer 2020, the first international …

The vulnerability of artificial intelligence (AI) and machine learning (ML) against adversarial
disturbances and attacks significantly restricts their applicability in safety-critical systems …

We introduce sparse polynomial zonotopes, a new set representation for formal verification
of hybrid systems. Sparse polynomial zonotopes can represent nonconvex sets and are …

Control systems can be subject to outside inputs, environmental effects, disturbances, and
sensor/actuator inaccuracy. To model such systems, linear differential equations with …

A graduate-level textbook that presents a unified mathematical framework for modeling and
analyzing cyber-physical systems, with a strong focus on verification. Verification aims to …

Autonomous cyber-physical systems (CPS) rely on the correct operation of numerous
components, with state-of-the-art methods relying on machine learning (ML) and artificial …

As neural networks (NNs) become more prevalent in safety-critical applications such as
control of vehicles, there is a growing need to certify that systems with NN components are …