Publications associées à Fast Adversarial Training With Adaptive Step Size

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.

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Sabine Süsstrunk, Mathieu Salzmann, Yulun Jiang, Chen Liu, Zhuoyi Huang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023

Fast Adversarial Training With Adaptive Step Size

Graph Chatbot

Chattez avec Graph Search

Understanding generalization and robustness in modern deep learning

Revisiting Character-level Adversarial Attacks for Language Models

Deep Learning Generalization with Limited and Noisy Labels

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Robust Training and Verification of Deep Neural Networks

Adversarial training with informed data selection

Robustness and invariance properties of image classifiers

Robust Binary Models by Pruning Randomly-initialized Networks

Deep Generative Models for Autonomous Driving: from Motion Forecasting to Realistic Image Synthesis

Hamiltonian Deep Neural Networks Guaranteeing Non-Vanishing Gradients by Design

Revisiting Character-level Adversarial Attacks for Language Models

Understanding generalization and robustness in modern deep learning

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Robust Training and Verification of Deep Neural Networks

Deep Learning Generalization with Limited and Noisy Labels

Robustness and invariance properties of image classifiers

Robust Binary Models by Pruning Randomly-initialized Networks

Adversarial training with informed data selection