Secure multi-party computation (MPC) allows users to offload machine lea...
In today's machine learning (ML) models, any part of the training data c...
Privacy-preserving instance encoding aims to encode raw data as feature
...
Online personalized recommendation services are generally hosted in the ...
Deep learning-based personalized recommendation systems are widely used ...
In this paper, we propose STAMP, an end-to-end 3-party MPC protocol for
...
Federated learning (FL) aims to perform privacy-preserving machine learn...
Path planning for autonomous driving with dynamic obstacles poses a chal...
Localization and mapping is a key technology for bridging the virtual an...
Pruning is a popular technique for reducing the model size and computati...
Neural network robustness has become a central topic in machine learning...
This paper shows that today's wireless charging interface is vulnerable ...
Virtual memory has been a standard hardware feature for more than three
...
This paper proposes GuardNN, a secure deep neural network (DNN) accelera...
We characterize the growth of the Sibson mutual information, of any orde...
In this paper, we propose MgX, a near-zero overhead memory protection sc...
Side channels represent a broad class of security vulnerabilities that h...
We propose precision gating (PG), an end-to-end trainable dynamic
dual-p...
Employing deep neural networks to obtain state-of-the-art performance on...