Hardware security and trust have become a pressing issue during the last two decades due
to the globalization of the semiconductor supply chain and ubiquitous network connection of …

We investigate a new method for injecting backdoors into machine learning models, based
on compromising the loss-value computation in the model-training code. We use it to …

Diverse and wide-range applications of integrated circuits (ICs) and the development of
Cyber Physical System (CPS), more and more third-party manufacturers are involved in the …

Currently, machine learning (ML) techniques are at the heart of smart cyber-physical
systems (CPSs) and Internet-of-Things (loT). This article discusses various challenges and …

Despite the high accuracy achieved by the deep neural network (DNN) technique, there is
still a lack of satisfying methodologies to protect the intellectual property (IP) of DNNs, which …

Recent advances in neural networks (NNs) and their applications in deep learning
techniques have made the security aspects of NNs an important and timely topic for …

As the machine learning-related technology has made great progress in recent years, deep
neural networks are widely used in many scenarios, including security-critical ones, which …

The convergence of edge computing and deep learning empowers endpoint hardwares or
edge devices to perform inferences locally with the help of deep neural network (DNN) …

As “deep neural networks”(DNNs) achieve increasing accuracy, they are getting employed
in increasingly diverse applications, including security-critical applications such as medical …

With the fast evolvement of deep-learning specific embedded computing systems,
applications powered by deep learning are moving from the cloud to the edge. When …