We survey the adversarial robustness of neural networks from the perspective of Lipschitz
calculus in a unifying fashion by expressing models, attacks and safety guarantees, that is, a …

The right to be forgotten calls for efficient machine unlearning techniques that make trained
machine learning models forget a cohort of data. The combination of training and unlearning …

Recent findings have shown multiple graph learning models, such as graph classification
and graph matching, are highly vulnerable to adversarial attacks, ie small input …

Implicit neural networks, aka, deep equilibrium networks, are a class of implicit-depth
learning models where function evaluation is performed by solving a fixed point equation …

Despite the large success of deep neural networks (DNN) in recent years, most neural
networks still lack mathematical guarantees in terms of stability. For instance, DNNs are …

Softening material models are known to trigger spurious localizations. This may be shown
theoretically by the existence of solutions with zero dissipation when localization occurs and …

The successful incorporation of machine learning models into safety-critical control systems
requires rigorous robustness guarantees. Randomized smoothing remains one of the state …

Fast and precise Lipschitz constant estimation of neural networks is an important task for
deep learning. Researchers have recently found an intrinsic trade-off between the accuracy …

Transformer-based models, such as BERT and GPT, have been widely adopted in natural
language processing (NLP) due to their exceptional performance. However, recent studies …

Smoothness and low dimensional structures play central roles in improving generalization
and stability in learning and statistics. This work combines techniques from semi-infinite …