Publications associées à Empirical study of the topology and geometry of deep networks

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Square Attack: a query-efficient black-box adversarial attack via random search

Nicolas Henri Bernard Flammarion, Maksym Andriushchenko, Francesco Croce

We propose the Square Attack, a new score-based black-box

l_2

and

l_\infty

adversarial attack that does not rely on local gradient information and thus is not affected by gradient masking. The Square Attack is based on a randomized search scheme where ...

2020

Empirical study of the topology and geometry of deep networks

Graph Chatbot

Chattez avec Graph Search

From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

Neural Anisotropy Directions

Square Attack: a query-efficient black-box adversarial attack via random search

Shape Reconstruction by Learning Differentiable Surface Representations

Geometry of adversarial robustness of deep networks: methods and applications

Biologically plausible deep learning – but how far can we go with shallow networks?

A jamming transition from under- to over-parametrization affects generalization in deep learning

SparseFool: a few pixels make a big difference

A geometry-inspired decision-based attack

Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness

Square Attack: a query-efficient black-box adversarial attack via random search

From Classical to Unsupervised-Deep-Learning Methods for Solving Inverse Problems in Imaging.

A geometry-inspired decision-based attack

Neural Anisotropy Directions

Shape Reconstruction by Learning Differentiable Surface Representations

Biologically plausible deep learning – but how far can we go with shallow networks?

Geometry of adversarial robustness of deep networks: methods and applications

A jamming transition from under- to over-parametrization affects generalization in deep learning

SparseFool: a few pixels make a big difference