Machine-Learning-as-a-Service providers expose machine learning (ML) models through
application programming interfaces (APIs) to developers. Recent work has shown that …

As a promising service, Machine Learning as a Service (MLaaS) provides personalized
inference functions for clients through paid APIs. Nevertheless, it is vulnerable to model …

Abstract Machine learning models are increasingly being deployed in practice. Machine
Learning as a Service (MLaaS) providers expose such models to queries by third-party …

Machine learning approaches have been increasingly applied to various applications for
data analytics (eg spam filtering, image classification). Further, with the growing adoption of …

Model extraction attacks are designed to steal trained models with only query access, as is
often provided through APIs that ML-as-a-Service providers offer. ML models are expensive …

Machine-Learning-as-a-Service (MLaaS) has become a widespread paradigm, making
even the most complex Machine Learning models available for clients via, eg, a pay-per …

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 …

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service
(MLaaS) platforms by``stealing''the functionality of confidential machine-learning models …

Abstract Machine Learning as a Service (MLaaS) is a popular and convenient way to access
a trained machine learning (ML) model trough an API. However, if the user's input is …

Machine learning is being increasingly used by individuals, research institutions, and
corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) …