Adversarial Robustness Via Fisher-Rao Regularization
Work
Year: 2022
Type: article
Abstract: Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle. We propose an information-geometric formulation of adve... more
Institutions McGill University, École de Technologie Supérieure, Centre National de la Recherche Scientifique, International Laboratory on Learning Systems
Cites: 63
Cited by: 20
Related to: 10
FWCI: 2.975
Citation percentile (by year/subfield): 100
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green