Model extraction attacks have become serious issues for service providers using machine
learning. We consider an adversarial setting to prevent model extraction under the …

The privacy of machine learning models has become a significant concern in many
emerging Machine-Learning-as-a-Service applications, where prediction services based on …

Model extraction increasingly attracts research attentions as keeping commercial AI models
private can retain a competitive advantage. In some scenarios, AI models are trained …

Machine learning (ML) and deep learning methods have become common and publicly
available, while ML security to date struggles to cope with rising threats. One rising threat is …

Machine learning models are vulnerable to simple model stealing attacks if the adversary
can obtain output labels for chosen inputs. To protect against these attacks, it has been …

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality
of ML models becomes paramount for two reasons:(a) a model can be a business …

Black-Box attacks on machine learning models occur when an attacker, despite having no
access to the inner workings of a model, can successfully craft an attack by means of model …

Current model extraction attacks assume that the adversary has access to a surrogate
dataset with characteristics similar to the proprietary data used to train the victim model. This …

Model inversion attacks involve reconstructing the training data of a target model, which
raises serious privacy concerns for machine learning models. However, these attacks …

Current model extraction attacks assume that the adversary has access to a surrogate
dataset with characteristics similar to the proprietary data used to train the victim model. This …