Abstract Context Machine Learning (ML) has been at the heart of many innovations over the
past years. However, including it in so-called “safety-critical” systems such as automotive or …

Deep Learning (DL) solutions are increasingly adopted, but how to test them remains a
major open research problem. Existing and new testing techniques have been proposed for …

Neural networks have had discernible achievements in a wide range of applications. The
wide-spread adoption also raises the concern of their dependability and reliability. Similar to …

We present NNrepair, a constraint-based technique for repairing neural network classifiers.
The technique aims to fix the logic of the network at an intermediate layer or at the last layer …

Deep neural networks (DNNs) are continuously expanding their application to various
domains due to their high performance. Nevertheless, a well-trained DNN after deployment …

Deep Learning (DL) components are routinely integrated into software systems that need to
perform complex tasks such as image or natural language processing. The adequacy of the …

Safety is a critical concern for the next generation of autonomy that is likely to rely heavily on
deep neural networks for perception and control. This paper proposes a method to repair …

Deep Neural Networks (DNNs) have achieved tremendous success in many applications,
while it has been demonstrated that DNNs can exhibit some undesirable behaviors on …

Although deep neural networks (DNNs) achieve rather high performance in many cutting-
edge applications (eg, autonomous driving, medical diagnose), their trustworthiness on real …

Systematic techniques to improve quality of deep neural networks (DNNs) are critical given
the increasing demand for practical applications including safety-critical ones. The key …