Enregistré dans:
Détails bibliographiques
Auteurs principaux: Korotkova, Kristina, Katrutsa, Aleksandr
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.10936
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914195732168704
author Korotkova, Kristina
Katrutsa, Aleksandr
author_facet Korotkova, Kristina
Katrutsa, Aleksandr
contents The construction of adversarial attacks for neural networks appears to be a crucial challenge for their deployment in various services. To estimate the adversarial robustness of a neural network, a fast and efficient approach is needed to construct adversarial attacks. Since the formalization of adversarial attack construction involves solving a specific optimization problem, we consider the problem of constructing an efficient and effective adversarial attack from a numerical optimization perspective. Specifically, we suggest utilizing advanced projection-free methods, known as modified Frank-Wolfe methods, to construct white-box adversarial attacks on the given input data. We perform a theoretical and numerical evaluation of these methods and compare them with standard approaches based on projection operations or geometrical intuition. Numerical experiments are performed on the MNIST and CIFAR-10 datasets, utilizing a multiclass logistic regression model, the convolutional neural networks (CNNs), and the Vision Transformer (ViT).
format Preprint
id arxiv_https___arxiv_org_abs_2512_10936
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
Korotkova, Kristina
Katrutsa, Aleksandr
Machine Learning
Artificial Intelligence
The construction of adversarial attacks for neural networks appears to be a crucial challenge for their deployment in various services. To estimate the adversarial robustness of a neural network, a fast and efficient approach is needed to construct adversarial attacks. Since the formalization of adversarial attack construction involves solving a specific optimization problem, we consider the problem of constructing an efficient and effective adversarial attack from a numerical optimization perspective. Specifically, we suggest utilizing advanced projection-free methods, known as modified Frank-Wolfe methods, to construct white-box adversarial attacks on the given input data. We perform a theoretical and numerical evaluation of these methods and compare them with standard approaches based on projection operations or geometrical intuition. Numerical experiments are performed on the MNIST and CIFAR-10 datasets, utilizing a multiclass logistic regression model, the convolutional neural networks (CNNs), and the Vision Transformer (ViT).
title Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.10936