Adversarial attacks can drastically change the output of a method by small alterations to its
input. While this can be a useful framework to analyze worst-case robustness, it can also be …

Robustness to malicious attacks is of paramount importance for distributed learning. Existing
works often consider the classical Byzantine attacks model, which assumes that some …

Deep learning has made remarkable progress over the past decade across various fields,
such as Computer Vision, Natural Language Processing (NLP), and Speech Recognition …