Deep neural networks are widely used for nonlinear function approximation, with
applications ranging from computer vision to control. Although these networks involve the …

We review state-of-the-art formal methods applied to the emerging field of the verification of
machine learning systems. Formal methods can provide rigorous correctness guarantees on …

Bound propagation methods, when combined with branch and bound, are among the most
effective methods to formally verify properties of deep neural networks such as correctness …

Bound propagation based incomplete neural network verifiers such as CROWN are very
efficient and can significantly accelerate branch-and-bound (BaB) based complete …

Formal approaches can provide strict correctness guarantees for the development of both
hardware and software systems. In this work, we examine state-of-the-art formal methods for …

This report summarizes the second International Verification of Neural Networks
Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for …

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 …

Linear relaxation based perturbation analysis (LiRPA) for neural networks, which computes
provable linear bounds of output neurons given a certain amount of input perturbation, has …

The optimization and machine learning toolkit (OMLT) is an open-source software package
incorporating neural network and gradient-boosted tree surrogate models, which have been …

We present COLT, a new method to train neural networks based on a novel combination of
adversarial training and provable defenses. The key idea is to model neural network training …