Search Results for author:
Found 9 papers, 7 papers with code
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization
However, its widespread adoption has been limited due to a reliance on tricks to generate interpretable images, and corresponding challenges in scaling it to deeper neural networks.
Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception
Harmonized DNNs achieve the best of both worlds and experience attacks that are detectable and affect features that humans find diagnostic for recognition, meaning that attacks on these models are more likely to be rendered ineffective by inducing similar effects on human perception.
DP-SGD Without Clipping: The Lipschitz Neural Network Way
To provide sensitivity bounds and bypass the drawbacks of the clipping process, we propose to rely on Lipschitz constrained networks.
Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
The distance to the support can be interpreted as a normality score, and its approximation using 1-Lipschitz neural networks provides robustness bounds against $l2$ adversarial attacks, an under-explored weakness of deep learning-based OCC algorithms.
CRAFT: Concept Recursive Activation FacTorization for Explainability
However, recent research has exposed the limited practical value of these methods, attributed in part to their narrow focus on the most prominent regions of an image -- revealing "where" the model looks, but failing to elucidate "what" the model sees in those areas.
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations. However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights.
Xplique: A Deep Learning Explainability Toolbox
Today's most advanced machine-learning models are hardly scrutable.
Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks
However they remain commonly considered as less accurate, and their properties in learning are still not fully understood.
Achieving robustness in classification using optimal transport with hinge regularization
This loss function has a direct interpretation in terms of adversarial robustness together with certifiable robustness bound.
