В работе рассматривается проблема атак на системы машинного обучения. Под
такими атаками понимаются специальные воздействия на элементы конвейера …

Deep Convolutional Neural Networks (DCNNs) have revolutionized and improved many
aspects of modern life. However, these models are increasingly more complex, and training …

Cloud hosting of quantum machine learning (QML) models exposes them to a range of
vulnerabilities, the most significant of which is the model stealing attack. In this study, we …

Users have renewed interest in protecting their private data in the digital space. When they
don't believe that their privacy is sufficiently covered by one platform, they will readily switch …

Heart disease is a leading global cause of death, while federated learning (FL) is an
effective way to predict it. Due to patient privacy concerns and the centralized nature of …

Differential Privacy has become a widely popular method for data protection in machine
learning, especially since it allows formulating strict mathematical privacy guarantees. This …

Diffusion models showcased strong capabilities in image synthesis, being used in many
computer vision tasks with great success. To this end, we propose to explore a new use …

Recent research has shown that an adversary can use a surrogate model to steal the
functionality of a target deep learning model even under the black-box condition and without …

In today's landscape, the widespread integration of artificial intelligence (AI) solutions across
diverse domains has become commonplace. Yet, despite its omnipresence, AI applications …

With the continuous promotion and deepened application of Machine Learning-as-a-Service
(MLaaS) across various societal domains, its privacy problems occur frequently and receive …