Skip to main navigation
Skip to search
Skip to main content
ÉTS Research Discovery Portal Home
Help & FAQ
Link opens in a new tab
Français
English
Search content at ÉTS Research Discovery Portal
Home
Profiles
Research units
Projects
Research output
Datasets
Press/Media
Student theses
Adversarial Robustness Via Fisher-Rao Regularization
Marine Picot
, Francisco Messina
, Malik Boudiaf
, Fabrice Labeau
,
Ismail Ben Ayed
, Pablo Piantanida
École de technologie supérieure
Systems Engineering Department
itechsanté - Research Institute for Innovation in Health Technologies
LIVIA - Imaging, Vision and Artificial Intelligence Laboratory
McGill University
Laboratoire des Signaux et Systèmes
École de technologie supérieure
Research output
:
Contribution to journal
›
Journal Article
›
peer-review
19
Citations (Scopus)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Adversarial Robustness Via Fisher-Rao Regularization'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
Keyphrases
Adversarial Defense
50%
Adversarial Robustness
100%
Categorical Cross-entropy Loss
50%
Fisher-Rao
100%
Fisher-Rao Distance
50%
Gaussian Model
50%
Geodesic Distance
50%
Geometric Formulation
50%
Geometric Properties
50%
Machine Learning
50%
Multi-class
50%
Natural Input
50%
Neural Network
50%
Pareto Optimal Points
50%
Perturbed Inputs
50%
Robust Performance
50%
Robust Region
50%
Simple Linear Model
50%
Softmax
100%
State-of-the-art Techniques
50%
Training Time
50%
Computer Science
Adversarial Robustness
100%
Entropy
33%
Gaussian Model
33%
Geodesic Distance
33%
Geometric Information
66%
Learning System
33%
Machine Learning
33%
Multiclass Case
33%
Neural Network
33%
Regularization
100%
Robustness Region
33%
Mathematics
Adversarial Robustness
100%
Cross-Entropy
33%
Gaussian Distribution
33%
Input Feature
33%
Neural Network
33%
Pareto Optimal
33%
Regularization
100%