498 citations · 717 across the 28 of their papers we have counts for
7 papers · 1 filter
AutoReP: Automatic ReLU Replacement for Fast Private Network Inference
Hongwu Peng, Shaoyi Huang, Tong Zhou +11
The growth of the Machine-Learning-As-A-Service (MLaaS) market has highlighted clients' data privacy and security issues. Private inference (PI) techniques using cryptographic prim…
PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network Deployment
Hongwu Peng, Shanglin Zhou, Yukui Luo +9
Two-party computation (2PC) is promising to enable privacy-preserving deep learning (DL). However, the 2PC-based privacy-preserving DL implementation comes with high comparison pro…
RRNet: Towards ReLU-Reduced Neural Network for Two-party Computation Based Private Inference
Hongwu Peng, Shanglin Zhou, Yukui Luo +11
The proliferation of deep learning (DL) has led to the emergence of privacy and security concerns. To address these issues, secure Two-party computation (2PC) has been proposed as…
CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference
Ran Ran, Nuo Xu, Wei Wang +3
Recently cloud-based graph convolutional network (GCN) has demonstrated great success and potential in many privacy-sensitive applications such as personal healthcare and financial…
PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inference
Hongwu Peng, Shanglin Zhou, Yukui Luo +10
The rapid growth and deployment of deep learning (DL) has witnessed emerging privacy and security concerns. To mitigate these issues, secure multi-party computation (MPC) has been…
NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks
Nuo Xu, Binghui Wang, Ran Ran +2
Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training. In this paper, we propose…
Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks
Siyue Wang, Xiao Wang, Pu Zhao +4
Deep neural networks (DNNs) are known vulnerable to adversarial attacks. That is, adversarial examples, obtained by adding delicately crafted distortions onto original legal inputs…