10 citations · 36 across the 22 of their papers we have counts for
22 papers
ShuffleV: A Microarchitectural Defense Strategy against Electromagnetic Side-Channel Attacks in Microprocessors
Nuntipat Narkthong, Yukui Luo, Xiaolin Xu
The run-time electromagnetic (EM) emanation of microprocessors presents a side-channel that leaks the confidentiality of the applications running on them. Many recent works have de…
Towards Vector Optimization on Low-Dimensional Vector Symbolic Architecture
Shijin Duan, Yejia Liu, Gaowen Liu +3
Vector Symbolic Architecture (VSA) is emerging in machine learning due to its efficiency, but they are hindered by issues of hyperdimensionality and accuracy. As a promising mitiga…
AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
Tong Zhou, Jiahui Zhao, Yukui Luo +4
Private inference (PI) has emerged as a promising solution to execute computations on encrypted data, safeguarding user privacy and model parameters in edge computing. However, exi…
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…
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Tong Zhou, Xuandong Zhao, Xiaolin Xu +1
Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when comba…
TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments
Ziyu Liu, Tong Zhou, Yukui Luo +1
Trusted Execution Environments (TEEs) have become a promising solution to secure DNN models on edge devices. However, the existing solutions either provide inadequate protection or…
Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfaces
Yejia Liu, Shijin Duan, Xiaolin Xu +1
Brain-Computer interfaces (BCIs) are typically designed to be lightweight and responsive in real-time to provide users timely feedback. Classical feature engineering is computation…
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…
LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
Hongwu Peng, Ran Ran, Yukui Luo +8
The growth of Graph Convolution Network (GCN) model sizes has revolutionized numerous applications, surpassing human performance in areas such as personal healthcare and financial…
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…
VertexSerum: Poisoning Graph Neural Networks for Link Inference
Ruyi Ding, Shijin Duan, Xiaolin Xu +1
Graph neural networks (GNNs) have brought superb performance to various applications utilizing graph structural data, such as social analysis and fraud detection. The graph links,…
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…
NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation
Tong Zhou, Yukui Luo, Shaolei Ren +1
As a type of valuable intellectual property (IP), deep neural network (DNN) models have been protected by techniques like watermarking. However, such passive model protection canno…
MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption
Yejia Liu, Shijin Duan, Xiaolin Xu +1
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 propose MetaLDC, which met…
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…
ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach
Tong Zhou, Shaolei Ren, Xiaolin Xu
Malicious architecture extraction has been emerging as a crucial concern for deep neural network (DNN) security. As a defense, architecture obfuscation is proposed to remap the vic…
LeHDC: Learning-Based Hyperdimensional Computing Classifier
Shijin Duan, Yejia Liu, Shaolei Ren +1
Thanks to the tiny storage and efficient execution, hyperdimensional Computing (HDC) is emerging as a lightweight learning framework on resource-constrained hardware. Nonetheless,…
A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices
Shijin Duan, Xiaolin Xu, Shaolei Ren
By mimicking brain-like cognition and exploiting parallelism, hyperdimensional computing (HDC) classifiers have been emerging as a lightweight framework to achieve efficient on-dev…
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…
A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework
Yifan Gong, Zheng Zhan, Zhengang Li +8
Weight pruning of deep neural networks (DNNs) has been proposed to satisfy the limited storage and computing capability of mobile edge devices. However, previous pruning methods ma…