Machine learning (ML) is increasingly being adopted in a wide variety of application
domains. Usually, a well-performing ML model relies on a large volume of training data and …

Secure two-party neural network inference (2PC-NN) can offer privacy protection for both the
client and the server and is a promising technique in the machine-learning-as-a-service …

Neural networks (NNs) have become one of the most important tools for artificial
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …

We initiate the study of private inference on Transformer-based models in the client-server
setting, where clients have private inputs and servers hold proprietary models. Our main …

Federated learning (FL) is an increasingly popular approach for machine learning (ML) in
cases where the training dataset is highly distributed. Clients perform local training on their …

The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

The advent of transformers has brought about significant advancements in traditional
machine learning tasks. However, their pervasive deployment has raised concerns about …

How can a model owner prove they trained their model according to the correct
specification? More importantly, how can they do so while preserving the privacy of the …

We studied 53 privacy-preserving neural-network papers in 2016-2022 based on
cryptography (without trusted processors or differential privacy), 16 of which only use …

Large transformer-based models have realized state-of-the-art performance on lots of real-
world tasks such as natural language processing and computer vision. However, with the …