2 papers
cs.DC2022
MixNN: A design for protecting deep learning models
Chao Liu, Hao Chen, Yusen Wu +1
In this paper, we propose a novel design, called MixNN, for protecting deep learning model structure and parameters. The layers in a deep learning model of MixNN are fully decentra…
cs.CR2021
Tolerating Adversarial Attacks and Byzantine Faults in Distributed Machine Learning
Yusen Wu, Hao Chen, Xin Wang +3
Adversarial attacks attempt to disrupt the training, retraining and utilizing of artificial intelligence and machine learning models in large-scale distributed machine learning sys…