8 citations · 21 across the 16 of their papers we have counts for
8 papers · 1 filter
ProDiF: Protecting Domain-Invariant Features to Secure Pre-Trained Models Against Extraction
Tong Zhou, Shijin Duan, Gaowen Liu +4
Pre-trained models are valuable intellectual property, capturing both domain-specific and domain-invariant features within their weight spaces. However, model extraction attacks th…
SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud
Shijin Duan, Chenghong Wang, Hongwu Peng +4
As privacy-preserving becomes a pivotal aspect of deep learning (DL) development, multi-party computation (MPC) has gained prominence for its efficiency and strong security. Howeve…
MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference
Ziyu Liu, Yukui Luo, Shijin Duan +2
Deep neural network (DNN) models have become prevalent in edge devices for real-time inference. However, they are vulnerable to model extraction attacks and require protection. Exi…
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…
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…
NNReArch: A Tensor Program Scheduling Framework Against Neural Network Architecture Reverse Engineering
Yukui Luo, Shijin Duan, Cheng Gongye +2
Architecture reverse engineering has become an emerging attack against deep neural network (DNN) implementations. Several prior works have utilized side-channel leakage to recover…
HDLock: Exploiting Privileged Encoding to Protect Hyperdimensional Computing Models against IP Stealing
Shijin Duan, Shaolei Ren, Xiaolin Xu
Hyperdimensional Computing (HDC) is facing infringement issues due to straightforward computations. This work, for the first time, raises a critical vulnerability of HDC, an attack…