Picture for Thibaut Boissin

Thibaut Boissin

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

Add code
Jun 11, 2023
Figure 1 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 2 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 3 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Figure 4 for Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
Viaarxiv icon

Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception

Add code
Jun 05, 2023
Viaarxiv icon

DP-SGD Without Clipping: The Lipschitz Neural Network Way

Add code
May 25, 2023
Figure 1 for DP-SGD Without Clipping: The Lipschitz Neural Network Way
Figure 2 for DP-SGD Without Clipping: The Lipschitz Neural Network Way
Figure 3 for DP-SGD Without Clipping: The Lipschitz Neural Network Way
Figure 4 for DP-SGD Without Clipping: The Lipschitz Neural Network Way
Viaarxiv icon

CRAFT: Concept Recursive Activation FacTorization for Explainability

Add code
Nov 17, 2022
Figure 1 for CRAFT: Concept Recursive Activation FacTorization for Explainability
Figure 2 for CRAFT: Concept Recursive Activation FacTorization for Explainability
Figure 3 for CRAFT: Concept Recursive Activation FacTorization for Explainability
Figure 4 for CRAFT: Concept Recursive Activation FacTorization for Explainability
Viaarxiv icon

When adversarial attacks become interpretable counterfactual explanations

Add code
Jun 14, 2022
Figure 1 for When adversarial attacks become interpretable counterfactual explanations
Figure 2 for When adversarial attacks become interpretable counterfactual explanations
Figure 3 for When adversarial attacks become interpretable counterfactual explanations
Figure 4 for When adversarial attacks become interpretable counterfactual explanations
Viaarxiv icon

Xplique: A Deep Learning Explainability Toolbox

Add code
Jun 09, 2022
Figure 1 for Xplique: A Deep Learning Explainability Toolbox
Viaarxiv icon

Achieving robustness in classification using optimal transport with hinge regularization

Add code
Jun 11, 2020
Figure 1 for Achieving robustness in classification using optimal transport with hinge regularization
Figure 2 for Achieving robustness in classification using optimal transport with hinge regularization
Figure 3 for Achieving robustness in classification using optimal transport with hinge regularization
Figure 4 for Achieving robustness in classification using optimal transport with hinge regularization
Viaarxiv icon