Search Results - "Duan, Shijin"

Plasmon enhanced Sn:In2O3/attapulgite S-scheme heterojunction for efficient photothermal reduction of CO2 by Cao, Guangbiao, Ye, Xuhua, Duan, Shijin, Cao, Ziwen, Zhang, Chunyan, Yao, Chao, Li, Xiazhang

“…Photothermal catalytic conversion of CO2 and H2O to solar fuels has great potential in industry but remains challenge using full solar spectrum. Herein,…”
Get full text

MirrorNet: A TEE-Friendly Framework for Secure On-Device DNN Inference by Liu, Ziyu, Luo, Yukui, Duan, Shijin, Zhou, Tong, Xu, Xiaolin

“…Deep neural network (DNN) models have become prevalent in edge devices for real-time inference. However, they are vulnerable to model extraction attacks and…”
Get full text

PASNet: Polynomial Architecture Search Framework for Two-party Computation-based Secure Neural Network Deployment by Peng, Hongwu, Zhou, Shanglin, Luo, Yukui, Xu, Nuo, Duan, Shijin, Ran, Ran, Zhao, Jiahui, Wang, Chenghong, Geng, Tong, Wen, Wujie, Xu, Xiaolin, Ding, Caiwen

“…Two-party computation (2PC) is promising to enable privacy-preserving deep learning (DL). However, the 2PC-based privacy-preserving DL implementation comes…”
Get full text

HDCOG: A Lightweight Hyperdimensional Computing Framework with Feature Extraction by Duan, Shijin, Xu, Xiaolin

“…As an emerging classification and recognition paradigms on nanoscale edge-devices, the performance (e.g., inference accuracy) of Hyperdimensional Computing…”
Get full text

Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfaces by Liu, Yejia, Duan, Shijin, Xu, Xiaolin, Ren, Shaolei

“…Brain-Computer interfaces (BCIs) are typically designed to be lightweight and responsive in real-time to provide users timely feedback. Classical feature…”
Get full text

MirrorNet: A TEE-Friendly Framework for Secure On-device DNN Inference by Liu, Ziyu, Luo, Yukui, Duan, Shijin, Zhou, Tong, Xu, Xiaolin

“…Deep neural network (DNN) models have become prevalent in edge devices for real-time inference. However, they are vulnerable to model extraction attacks and…”
Get full text

HDLock: Exploiting Privileged Encoding to Protect Hyperdimensional Computing Models against IP Stealing by Duan, Shijin, Ren, Shaolei, Xu, Xiaolin

“…Hyperdimensional Computing (HDC) is facing infringement issues due to straightforward computations. This work, for the first time, raises a critical…”
Get full text

A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices by Duan, Shijin, Xu, Xiaolin, Ren, Shaolei

“…By mimicking brain-like cognition and exploiting parallelism, hyperdimensional computing (HDC) classifiers have been emerging as a lightweight framework to…”
Get full text

A Survey of Recent Attacks and Mitigation on FPGA Systems by Duan, Shijin, Wang, Wenhao, Luo, Yukui, Xu, Xiaolin

“…The emergence of a large variety of compute-intensive applications has made hardware accelerators a new necessity to deploy the corresponding high-complexity…”
Get full text

VertexSerum: Poisoning Graph Neural Networks for Link Inference by Ding, Ruyi, Duan, Shijin, Xu, Xiaolin, Fei, Yunsi

“…Graph neural networks (GNNs) have brought superb performance to various applications utilizing graph structural data, such as social analysis and fraud…”
Get full text

Achieving Certified Robustness for Brain-Inspired Low-Dimensional Computing Classifiers by Yang, Fangfang, Duan, Shijin, Xu, Xiaolin, Ren, Shaolei

“…Brain-inspired hyperdimensional computing (HDC) in machine learning applications has been achieving great success in terms of energy efficiency and low…”
Get full text

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption by Liu, Yejia, Duan, Shijin, Xu, Xiaolin, Ren, Shaolei

“…Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we…”
Get full text

GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction by Duan, Shijin, Ding, Ruyi, He, Jiaxing, Ding, Aidong Adam, Fei, Yunsi, Xu, Xiaolin

“…Graph-structured data is integral to many applications, prompting the development of various graph representation methods. Graph autoencoders (GAEs), in…”
Get full text

NNReArch: A Tensor Program Scheduling Framework Against Neural Network Architecture Reverse Engineering by Luo, Yukui, Duan, Shijin, Gongye, Cheng, Fei, Yunsi, Xu, Xiaolin

“…Architecture reverse engineering has become an emerging attack against deep neural network (DNN) implementations. Several prior works have utilized…”
Get full text

A Cautionary Note on Building Multi-tenant Cloud-FPGA as a Secure Infrastructure by Luo, Yukui, Zhang, Yuheng, Duan, Shijin, Xu, Xiaolin

“…Security concerns have been raised for multi-tenant cloud-FPGA in many recent works. While these existing works focused on studying the security of diverse…”
Get full text

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud by Duan, Shijin, Wang, Chenghong, Peng, Hongwu, Luo, Yukui, Wen, Wujie, Ding, Caiwen, Xu, Xiaolin

“…As privacy-preserving becomes a pivotal aspect of deep learning (DL) development, multi-party computation (MPC) has gained prominence for its efficiency and…”
Get full text

Deep Neural Network Security From a Hardware Perspective by Zhou, Tong, Zhang, Yuheng, Duan, Shijin, Luo, Yukui, Xu, Xiaolin

“…Deep neural networks (DNNs) have been deployed on various computing platforms for acceleration, making the hardware security of DNNs an emerging concern…”
Get full text

NNReArch: A Tensor Program Scheduling Framework Against Neural Network Architecture Reverse Engineering by Luo, Yukui, Duan, Shijin, Gongye, Cheng, Fei, Yunsi, Xu, Xiaolin

“…Architecture reverse engineering has become an emerging attack against deep neural network (DNN) implementations. Several prior works have utilized…”
Get full text

LeHDC: Learning-Based Hyperdimensional Computing Classifier by Duan, Shijin, Liu, Yejia, Ren, Shaolei, Xu, Xiaolin

“…Thanks to the tiny storage and efficient execution, hyperdimensional Computing (HDC) is emerging as a lightweight learning framework on resource-constrained…”
Get full text

AQ2PNN: Enabling Two-party Privacy-Preserving Deep Neural Network Inference with Adaptive Quantization by Luo, Yukui, Xu, Nuo, Peng, Hongwu, Wang, Chenghong, Duan, Shijin, Mahmood, Kaleel, Wen, Wujie, Ding, Caiwen, Xu, Xiaolin

“…The growing prevalence of Machine Learning as a Service (MLaaS) enables a wide range of applications but simultaneously raises numerous security and privacy…”
Get full text