{"ID":2830406,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.10936","arxiv_id":"2512.10936","title":"Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks","abstract":"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).","short_abstract":"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 cons...","url_abs":"https://arxiv.org/abs/2512.10936","url_pdf":"https://arxiv.org/pdf/2512.10936v1","authors":"[\"Kristina Korotkova\",\"Aleksandr Katrutsa\"]","published":"2025-12-11T18:58:17Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Vision Transformer\",\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}