Publication

Logit Pairing Methods Can Fool Gradient-Based Attacks

Publications associées (32)

Graph Chatbot

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.

Connectez-vous pour utiliser Chat avec Graph Search

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Revisiting Character-level Adversarial Attacks for Language Models

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu, Elias Abad Rocamora

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

2024

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

Fast Adversarial Training With Adaptive Step Size

Sabine Süsstrunk, Mathieu Salzmann, Chen Liu, Zhuoyi Huang, Yong Zhang, Jue Wang

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

Piscataway2023

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Florent Gérard Krzakala, Lenka Zdeborová, Hugo Chao Cui

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

2023

Adversarial vulnerability bounds for Gaussian process classification

Kathrin Grosse

Protecting ML classifiers from adversarial examples is crucial. We propose that the main threat is an attacker perturbing a confidently classified input to produce a confident misclassification. We consider in this paper the attack in which a small number ...

2023

Block-Sparse Adversarial Attack To Fool Transformer-Based Text Classifiers

Pascal Frossard, Seyedeh Sahar Sadrizadeh

Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this paper, we propose a gradient-based adversarial attack against transformer-based tex ...

IEEE2022

Towards Verifiable, Generalizable and Efficient Robust Deep Neural Networks.

Chen Liu

In the last decade, deep neural networks have achieved tremendous success in many fields of machine learning.However, they are shown vulnerable against adversarial attacks: well-designed, yet imperceptible, perturbations can make the state-of-the-art deep ...

EPFL2022

Robustness and invariance properties of image classifiers

Apostolos Modas

Deep neural networks have achieved impressive results in many image classification tasks. However, since their performance is usually measured in controlled settings, it is important to ensure that their decisions remain correct when deployed in noisy envi ...

EPFL2022

, , ,

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

2022