Deep Learning algorithms have achieved state-of-the-art performance for Image
Classification. For this reason, they have been used even in security-critical applications …

Today's world is highly network interconnected owing to the pervasiveness of small personal
devices (eg, smartphones) as well as large computing devices or services (eg, cloud …

Deep neural networks (DNNs) are an indispensable machine learning tool despite the
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …

With the rapid developments of artificial intelligence (AI) and deep learning (DL) techniques,
it is critical to ensure the security and robustness of the deployed algorithms. Recently, the …

We present a novel method for scalable and precise certification of deep neural networks.
The key technical insight behind our approach is a new abstract domain which combines …

With rapid progress and significant successes in a wide spectrum of applications, deep
learning is being applied in many safety-critical environments. However, deep neural …

We present a new method and system, called DeepZ, for certifying neural network
robustness based on abstract interpretation. Compared to state-of-the-art automated …

We propose a method to learn deep ReLU-based classifiers that are provably robust against
norm-bounded adversarial perturbations on the training data. For previously unseen …

Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

Neural networks have demonstrated considerable success on a wide variety of real-world
problems. However, networks trained only to optimize for training accuracy can often be …