Abstract Machine learning models trained by large volume of proprietary data and intensive
computational resources are valuable assets of their owners, who merchandise these …

Machine learning service API allows model owners to monetize proprietary models by
offering prediction services to third-party users. However, existing literature shows that …

Public intelligent services enabled by machine learning algorithms are vulnerable to model
extraction attacks that can steal confidential information of the learning models through …

The unprecedented success of deep learning is largely dependent on the availability of
massive amount of training data. In many cases, these data are crowd-sourced and may …

Membership Inference Attack (MIA) in deep learning is a common form of privacy attack
which aims to infer whether a data sample is in a target classifier's training dataset or not …

Data holders are increasingly seeking to protect their user's privacy, whilst still maximizing
their ability to produce machine learning (ML) models with high quality predictions. In this …

Machine learning models are increasingly made available to the masses through public
query interfaces. Recent academic work has demonstrated that malicious users who can …

Machine learning models are vulnerable to data inference attacks, such as membership
inference and model inversion attacks. In these types of breaches, an adversary attempts to …

Deep learning models have achieved great success in many real-world tasks such as image
recognition, machine translation, and self-driving cars. A large amount of data are needed to …

In model extraction attacks, adversaries can steal a machine learning model exposed via a
public API by repeatedly querying it and adjusting their own model based on obtained …