Speech and speaker recognition systems are employed in a variety of applications, from
personal assistants to telephony surveillance and biometric authentication. The wide …

Many companies provide neural network prediction services to users for a wide range of
applications. However, current prediction systems compromise one party's privacy: either the …

We introduce CryptGPU, a system for privacy-preserving machine learning that implements
all operations on the GPU (graphics processing unit). Just as GPUs played a pivotal role in …

Abstract The Right to be Forgotten is part of the recently enacted General Data Protection
Regulation (GDPR) law that affects any data holder that has data on European Union …

We study the problem of model extraction in natural language processing, in which an
adversary with only query access to a victim model attempts to reconstruct a local copy of …

High-performance Deep Neural Networks (DNNs) are increasingly deployed in many real-
world applications eg, cloud prediction APIs. Recent advances in model functionality …

We argue that the machine learning problem of model extraction is actually a cryptanalytic
problem in disguise, and should be studied as such. Given oracle access to a neural …

In Machine Learning as a Service, a provider trains a deep neural network and gives many
users access. The hosted (source) model is susceptible to model stealing attacks, where an …

Training machine learning (ML) models typically involves expensive iterative optimization.
Once the model's final parameters are released, there is currently no mechanism for the …

Neural Network (NN) accelerators are currently widely deployed in various security-crucial
scenarios, including image recognition, natural language processing and autonomous …