498 citations · 717 across the 28 of their papers we have counts for
29 papers
Evaluating Hybrid Quantum-Classical Models for Reduced-Order Brain Deformation Dynamics
Tao Liu, Ge He, Dongyu Liang +1
We evaluate hybrid quantum-classical machine learning for the reduced-order prediction of spatiotemporal brain deformation fields. To mitigate the computational intractability of h…
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…
Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise
Zheyu Yan, Yifan Qin, Wujie Wen +2
Compute-in-Memory (CiM), built upon non-volatile memory (NVM) devices, is promising for accelerating deep neural networks (DNNs) owing to its in-situ data processing capability and…
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…
NeFT: Negative Feedback Training to Improve Robustness of Compute-In-Memory DNN Accelerators
Yifan Qin, Zheyu Yan, Dailin Gan +5
Compute-in-memory accelerators built upon non-volatile memory devices excel in energy efficiency and latency when performing deep neural network (DNN) inference, thanks to their in…
Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration
Shaoyi Huang, Haowen Fang, Kaleel Mahmood +7
Biologically inspired Spiking Neural Networks (SNNs) have attracted significant attention for their ability to provide extremely energy-efficient machine intelligence through event…
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…
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Nuo Xu, Kaleel Mahmood, Haowen Fang +3
Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performance. However, unlike traditional deep le…
A Length Adaptive Algorithm-Hardware Co-design of Transformer on FPGA Through Sparse Attention and Dynamic Pipelining
Hongwu Peng, Shaoyi Huang, Shiyang Chen +8
Transformers are considered one of the most important deep learning models since 2018, in part because it establishes state-of-the-art (SOTA) records and could potentially replace…
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…
Achieving Real-Time LiDAR 3D Object Detection on a Mobile Device
Pu Zhao, Wei Niu, Geng Yuan +7
3D object detection is an important task, especially in the autonomous driving application domain. However, it is challenging to support the real-time performance with the limited…
Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspective
Shao-Cheng Wen, Yu-Jen Chen, Zihao Liu +7
Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically ana…
Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation
Xiaolong Ma, Geng Yuan, Sheng Lin +6
The state-of-art DNN structures involve intensive computation and high memory storage. To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suit…
Thread Batching for High-performance Energy-efficient GPU Memory Design
Bing Li, Mengjie Mao, Xiaoxiao Liu +6
Massive multi-threading in GPU imposes tremendous pressure on memory subsystems. Due to rapid growth in thread-level parallelism of GPU and slowly improved peak memory bandwidth, t…
Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds
Zihao Liu, Xiaowei Xu, Tao Liu +7
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly l…
Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM
Shaokai Ye, Xiaoyu Feng, Tianyun Zhang +11
Weight pruning and weight quantization are two important categories of DNN model compression. Prior work on these techniques are mainly based on heuristics. A recent work developed…
E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs
Zhe Li, Caiwen Ding, Siyue Wang +8
Recurrent Neural Networks (RNNs) are becoming increasingly important for time series-related applications which require efficient and real-time implementations. The two major types…
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…
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers
Tianyun Zhang, Shaokai Ye, Kaiqi Zhang +4
Weight pruning methods for deep neural networks (DNNs) have been investigated recently, but prior work in this area is mainly heuristic, iterative pruning, thereby lacking guarante…
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks
Qi Liu, Tao Liu, Zihao Liu +3
DNN is presenting human-level performance for many complex intelligent tasks in real-world applications. However, it also introduces ever-increasing security concerns. For example,…
DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework
Zihao Liu, Tao Liu, Wujie Wen +4
As one of most fascinating machine learning techniques, deep neural network (DNN) has demonstrated excellent performance in various intelligent tasks such as image classification.…
MT-Spike: A Multilayer Time-based Spiking Neuromorphic Architecture with Temporal Error Backpropagation
Tao Liu, Zihao Liu, Fuhong Lin +3
Modern deep learning enabled artificial neural networks, such as Deep Neural Network (DNN) and Convolutional Neural Network (CNN), have achieved a series of breaking records on a b…