We show how perturbing inputs to machine learning services (ML-service) deployed in the
cloud can protect against model stealing attacks. In our formulation, there is an ML-service …

Machine learning models have achieved state-of-the-art performance in various fields, from
image classification to speech recognition. However, such models are trained with a large …

Machine learning architectures are readily available, but obtaining the high quality labeled
data for training is costly. Pre-trained models available as cloud services can be used to …

Modern AI is largely driven by machine learning. Recent machine learning algorithms such
as deep neural networks (DNN) have become quite effective in many recognition tasks eg …

Model extraction (ME) attacks have been shown to cause financial losses for Machine-
Learning-as-a-Service (MLaaS) providers. Attackers steal ML models on MLaaS platforms …

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) …

Training a Deep Learning (DL) model requires proprietary data and computing-intensive
resources. To recoup their training costs, a model provider can monetize DL models through …

Machine Learning as a Service (MLaaS) platforms have gained popularity due to their
accessibility, cost-efficiency, scalability, and rapid development capabilities. However …

Machine learning as a Service (MLaaS) allows users to query the machine learning model
in an API manner, which provides an opportunity for users to enjoy the benefits brought by …

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