Data confidentiality is a central concern in modern computer systems and services, as
sensitive data from users and companies are being increasingly delegated to such systems …

On-device ML introduces new security challenges: DNN models become white-box
accessible to device users. Based on white-box information, adversaries can conduct …

Intel Software Guard eXtension (SGX) is the cornerstone of Confidential Computing,
enabling runtime code and data integrity and confidentiality via enclaves. Unfortunately …

Federated learning (FL) is a general principle for decentralized clients to train a server
model collectively without sharing local data. FL is a promising framework with practical …

This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based
protection for user data and model parameters even in an untrusted environment. GuardNN …

Trusted execution environments (TEEs) are widely employed to protect deep neural
networks (DNNs) from untrusted hosts (eg, hypervisors). By shielding DNNs as fully black …

Shielding neural networks (NNs) from untrusted hosts with Trusted Execution Environments
(TEEs) has been increasingly adopted. Nevertheless, this paper shows that the …

Model compression is a widely-used approach for reducing the size of deep learning
models without much accuracy loss, enabling resource-hungry models to be compressed for …

Recommenders are central in many applications today. The most effective recommendation
schemes, such as those based on collaborative filtering (CF), exploit similarities between …

This paper proposes GuardNN, a secure DNN accelerator that provides hardware-based
protection for user data and model parameters even in an untrusted environment. GuardNN …