Adversarial augmentation can improve adversarial robustness better than double the labelled data

Lockshin, N.; Khvostikov, A.; Krylov, A.

Авторы: Lockshin Nikita, Khvostikov Alexander, Krylov Andrey
Журнал: Pattern Recognition and Image Analysis: Advances in Mathematical Theory and Applications
Том: 34
Номер: 4
Год издания: 2024
Издательство: Pleiades Publishing, Ltd
Местоположение издательства: Road Town, United Kingdom
Первая страница: 1007
Последняя страница: 1014
DOI: 10.1134/S1054661824701025
Аннотация: The paper touches on the problem of adversarial augmentation of a dataset of images in order to improve the robustness of neural network classifiers to adversarial attacks. In recent years, neural network methods have developed significantly, new neural network methods show impressive results, but they are subject to so-called adversarial attacks - that is, they make incorrect predictions on inputs obtained as a result of imposing carefully crafted noise on the image. Because of this, the reliability of neural network methods is still a relevant area of study. This paper compares two image augmentation methods: by means of adversarial augmentation and by means of increasing the training set with new images. In particular, results suggest that a neural network trained on 50% of training images with adversarial augmentation demonstrates a higher accuracy (89.14%) on the test data with an adversarial attack imposed than a similar neural network trained on 100% of training images without adversarial augmentation (87.53%).
Добавил в систему: Сорокин Дмитрий Васильевич

	ИСТИНА	Войти в систему Регистрация
	ИСТИНА ПсковГУ
	Главная Поиск Статистика О проекте Помощь

ИСТИНА

ИСТИНА ПсковГУ

Adversarial augmentation can improve adversarial robustness better than double the labelled dataстатья

Прикрепленные файлы