Neural networks have achieved remarkable performance across various problem domains,
but their widespread applicability is hindered by inherent limitations such as overconfidence …

Abstract Deep Neural Networks have achieved extraordinary results on image classification
tasks, but have been shown to be vulnerable to attacks with carefully crafted perturbations of …

Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to
deal with uncertainty when learning from finite data. Among approaches to realize …

We propose a novel framework PROVEN to\textbf {PRO} babilistically\textbf {VE} rify\textbf
{N} eural network's robustness with statistical guarantees. PROVEN provides probability …

We investigate deep Bayesian neural networks with Gaussian priors on the weights and a
class of ReLU-like nonlinearities. Bayesian neural networks with Gaussian priors are well …

Uncertainty quantification of neural networks is critical to measuring the reliability and
robustness of deep learning systems. However, this often involves costly or inaccurate …

Quantifying the robustness of neural networks or verifying their safety properties against
input uncertainties or adversarial attacks have become an important research area in …

This work tackles the problem of characterizing and understanding the decision boundaries
of neural networks with piecewise linear non-linearity activations. We use tropical geometry …

Despite the impressive performance of Deep Neural Networks (DNNs) on various vision
tasks, they still exhibit erroneous high sensitivity toward semantic primitives (eg object pose) …

Many applications in aerodynamics depend on the use of sensors to estimate the evolving
state of the flow. In particular, a wide variety of traditional and learning-based strategies for …