Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

Training certifiably robust neural networks remains a notoriously hard problem. While
adversarial training optimizes under-approximations of the worst-case loss, which leads to …

We present a novel approach to efficiently compute tight non-convex enclosures of the
image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation …

Recent research has proposed various methods to formally verify neural networks against
minimal input perturbations; this verification task is also known as local robustness …

We present DeepDECS, a new method for the synthesis of correct-by-construction software
controllers for autonomous systems that use deep neural network (DNN) classifiers for the …

Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …

Bound propagation with branch-and-bound (BaB) is so far among the most effective
methods for neural network (NN) verification. However, existing works with BaB have mostly …

As robustness verification methods are becoming more precise, training certifiably robust
neural networks is becoming ever more relevant. To this end, certified training methods …

As a new programming paradigm, deep learning (DL) has achieved impressive performance
in areas such as image processing and speech recognition, and has expanded its …

Deep Neural Networks (DNNs) have emerged as an effective approach to tackling real-
world problems. However, like human-written software, DNNs can have bugs and can be …