|
ИСТИНА |
Войти в систему Регистрация |
ИПМех РАН |
||
On Model Inversion Attacksстатья
- Авторы: Junzhe Song, Namiot Dmitry
- Сборник: Distributed Computer and Communication Networks: Control, Computation, Communications (DCCN-2022) : материалы XXV международной научной конференции: Москва, 26–30 сентября 2022 года / под общ. ред. В. М. Вишневского и К. Е. Самуйлова
- Год издания: 2022
- Место издания: РУДН Москва
- Первая страница: 134
- Последняя страница: 142
- Аннотация: Attacks on machine learning systems are defined as special actions on the elements of the machine learning pipeline, which are designed to either prevent the normal operation of machine learning systems or ensure their special functioning,which is necessary for the attacker. Model inversion attacks aim to expose the private data used to train the model. Attacks that expose private informationabout machine learning systems are a big threat to machine learning as a service projects. In this article, we provide an overview of off-the-shelf software tools for performing model inversion attacks.
- Добавил в систему: Намиот Дмитрий Евгеньевич