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 …

AI has provided us with the ability to automate tasks, extract information from vast amounts of
data, and synthesize media that is nearly indistinguishable from the real thing. However …

In a model extraction attack, an adversary steals a copy of a remotely deployed machine
learning model, given oracle prediction access. We taxonomize model extraction attacks …

Most current approaches for protecting privacy in machine learning (ML) assume that
models exist in a vacuum. Yet, in reality, these models are part of larger systems that include …

Machine learning involves expensive data collection and training procedures. Model owners
may be concerned that valuable intellectual property can be leaked if adversaries mount …

Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …

Deep neural networks (DNNs) have a wide range of applications, and software employing
them must be thoroughly tested, especially in safety-critical domains. However, traditional …

Deep Neural Networks (DNNs) are fast becoming ubiquitous for their ability to attain good
accuracy in various machine learning tasks. A DNN's architecture (ie, its hyperparameters) …

Recent advancements in Deep Neural Networks (DNNs) have enabled widespread
deployment in multiple security-sensitive domains. The need for resource-intensive training …

The rapid development of artificial intelligence, especially deep learning technology, has
advanced autonomous driving systems (ADSs) by providing precise control decisions to …