The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …

In the past few years, it has become increasingly evident that deep neural networks are not
resilient enough to withstand adversarial perturbations in input data, leaving them …

Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …

Bayesian neural networks (BNN) and deep ensembles are principled approaches to
estimate the predictive uncertainty of a deep learning model. However their practicality in …

We show how to turn any classifier that classifies well under Gaussian noise into a new
classifier that is certifiably robust to adversarial perturbations under the L2 norm. While this" …

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 …

Adversarial training based on the minimax formulation is necessary for obtaining adversarial
robustness of trained models. However, it is conservative or even pessimistic so that it …

In this paper, we exploit the properties of mean absolute error (MAE) as a loss function for
the deep neural network (DNN) based vector-to-vector regression. The goal of this work is …

Finding minimum distortion of adversarial examples and thus certifying robustness in neural
networks classifiers is known to be a challenging problem. Nevertheless, recently it has …

Tight estimation of the Lipschitz constant for deep neural networks (DNNs) is useful in many
applications ranging from robustness certification of classifiers to stability analysis of closed …