661 citations · 2k across the 35 of their papers we have counts for
7 papers · 1 filter
HCE: Improving Performance and Efficiency with Heterogeneously Compressed Neural Network Ensemble
Jingchi Zhang, Huanrui Yang, Hai Li
Ensemble learning has gain attention in resent deep learning research as a way to further boost the accuracy and generalizability of deep neural network (DNN) models. Recent ensemb…
Privacy Leakage of Adversarial Training Models in Federated Learning Systems
Jingyang Zhang, Yiran Chen, Hai Li
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerabl…
Improving Adversarial Robustness in Weight-quantized Neural Networks
Chang Song, Elias Fallon, Hai Li
Neural networks are getting deeper and more computation-intensive nowadays. Quantization is a useful technique in deploying neural networks on hardware platforms and saving computa…
Snooping Attacks on Deep Reinforcement Learning
Matthew Inkawhich, Yiran Chen, Hai Li
Adversarial attacks have exposed a significant security vulnerability in state-of-the-art machine learning models. Among these models include deep reinforcement learning agents. Th…
LEASGD: an Efficient and Privacy-Preserving Decentralized Algorithm for Distributed Learning
Hsin-Pai Cheng, Patrick Yu, Haojing Hu +4
Distributed learning systems have enabled training large-scale models over large amount of data in significantly shorter time. In this paper, we focus on decentralized distributed…
Towards Efficient and Secure Delivery of Data for Training and Inference with Privacy-Preserving
Juncheng Shen, Juzheng Liu, Yiran Chen +1
Privacy recently emerges as a severe concern in deep learning, that is, sensitive data must be prohibited from being shared with the third party during deep neural network developm…
TernGrad: Ternary Gradients to Reduce Communication in Distributed Deep Learning
Wei Wen, Cong Xu, Feng Yan +4
High network communication cost for synchronizing gradients and parameters is the well-known bottleneck of distributed training. In this work, we propose TernGrad that uses ternary…