Providing non-trivial certificates of safety for non-linear stochastic systems is an important
open problem. One promising solution to address this problem is the use of barrier functions …

Approximate Bayesian inference for neural networks is considered a robust alternative to
standard training, often providing good performance on out-of-distribution data. However …

We consider the problem of certifying the individual fairness (IF) of feed-forward neural
networks (NNs). In particular, we work with the $\epsilon $-$\delta $-IF formulation, which …

Providing formal guarantees of algorithmic fairness is of paramount importance to socially
responsible deployment of machine learning algorithms. In this work, we study formal …

Post-hoc explanation methods are used with the intent of providing insights about neural
networks and are sometimes said to help engender trust in their outputs. However, popular …

This work takes a critical look at the application of conventional machine learning methods
to wireless communication problems through the lens of reliability and robustness. Deep …

With increased adoption of supervised deep learning methods for work with cosmological
survey data, the assessment of data perturbation effects (that can naturally occur in the data …

In this paper, we introduce BNN-DP, an efficient algorithmic framework for analysis of
adversarial robustness of Bayesian Neural Networks (BNNs). Given a compact set of input …

We present a new algorithm to train a robust malware detector. Malware is a prolific problem
and malware detectors are a front-line defense. Modern detectors rely on machine learning …

We consider the problem of computing reach-avoid probabilities for iterative predictions
made with Bayesian neural network (BNN) models. Specifically, we leverage bound …