Chordal and factor-width decomposition methods for semidefinite programming and
polynomial optimization have recently enabled the analysis and control of large-scale linear …

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 …

Neural networks have been widely applied in security applications such as spam and
phishing detection, intrusion prevention, and malware detection. This black-box method …

In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …

Lipschitz constant estimation plays an important role in understanding generalization,
robustness, and fairness in deep learning. Unlike naive bounds based on the network …

We present a novel semidefinite programming (SDP) relaxation that enables tight and
efficient verification of neural networks. The tightness is achieved by combining SDP …

Voice assistants offer a convenient and hands-free way of accessing computing in the home,
but a key problem with speech as an interaction modality is how to scaffold accurate mental …

Formal verification has emerged as a powerful approach to ensure the safety and reliability
of deep neural networks. However, current verification tools are limited to only a handful of …

The prevalence of neural networks in applications is expanding at an increasing rate. It is
becoming clear that providing robust guarantees on systems that use neural networks is …

We present a novel and computationally efficient method for repairing a feed-forward neural
network with respect to a finite set of inputs that are misclassified. The method assumes no …