Search Results for author: Wujie Wen

Found 28 papers, 7 papers with code

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud

no code implementations4 Jun 2024 Shijin Duan, Chenghong Wang, Hongwu Peng, Yukui Luo, Wujie Wen, Caiwen Ding, Xiaolin Xu

The primary challenge lies in the reliance of current MPC approaches on additive secret sharing, which incurs significant communication overhead with non-linear operations such as comparisons.

Cloud Computing Privacy Preserving

TSB: Tiny Shared Block for Efficient DNN Deployment on NVCIM Accelerators

no code implementations8 May 2024 Yifan Qin, Zheyu Yan, Zixuan Pan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

Compute-in-memory (CIM) accelerators using non-volatile memory (NVM) devices offer promising solutions for energy-efficient and low-latency Deep Neural Network (DNN) inference execution.

Zero-Space Cost Fault Tolerance for Transformer-based Language Models on ReRAM

no code implementations22 Jan 2024 Bingbing Li, Geng Yuan, Zigeng Wang, Shaoyi Huang, Hongwu Peng, Payman Behnam, Wujie Wen, Hang Liu, Caiwen Ding

Resistive Random Access Memory (ReRAM) has emerged as a promising platform for deep neural networks (DNNs) due to its support for parallel in-situ matrix-vector multiplication.

Improving Realistic Worst-Case Performance of NVCiM DNN Accelerators through Training with Right-Censored Gaussian Noise

no code implementations29 Jul 2023 Zheyu Yan, Yifan Qin, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

In this work, we propose to use the k-th percentile performance (KPP) to capture the realistic worst-case performance of DNN models executing on CiM accelerators.

Self-Driving Cars

Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filtering

no code implementations25 Jul 2023 Ce Feng, Nuo Xu, Wujie Wen, Parv Venkitasubramaniam, Caiwen Ding

In particular, for fully connected layers, we combine a block-circulant based spatial restructuring with Spectral-DP to achieve better utility.

Transfer Learning

Negative Feedback Training: A Novel Concept to Improve Robustness of NVCIM DNN Accelerators

1 code implementation23 May 2023 Yifan Qin, Zheyu Yan, Wujie Wen, Xiaobo Sharon Hu, Yiyu Shi

However, the stochastic nature and intrinsic variations of NVM devices often result in performance degradation in DNN inference.

Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration

no code implementations24 Apr 2023 Shaoyi Huang, Haowen Fang, Kaleel Mahmood, Bowen Lei, Nuo Xu, Bin Lei, Yue Sun, Dongkuan Xu, Wujie Wen, Caiwen Ding

Experimental results show that NDSNN achieves up to 20. 52\% improvement in accuracy on Tiny-ImageNet using ResNet-19 (with a sparsity of 99\%) as compared to other SOTA methods (e. g., Lottery Ticket Hypothesis (LTH), SET-SNN, RigL-SNN).

CryptoGCN: Fast and Scalable Homomorphically Encrypted Graph Convolutional Network Inference

2 code implementations24 Sep 2022 Ran Ran, Nuo Xu, Wei Wang, Gang Quan, Jieming Yin, Wujie Wen

To this end, we develop an approach that can effectively take advantage of the sparsity of matrix operations in GCN inference to significantly reduce the computational overhead.

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples

no code implementations7 Sep 2022 Nuo Xu, Kaleel Mahmood, Haowen Fang, Ethan Rathbun, Caiwen Ding, Wujie Wen

First, we show that successful white-box adversarial attacks on SNNs are highly dependent on the underlying surrogate gradient technique, even in the case of adversarially trained SNNs.

Adversarial Attack

EVE: Environmental Adaptive Neural Network Models for Low-power Energy Harvesting System

no code implementations14 Jul 2022 Sahidul Islam, Shanglin Zhou, Ran Ran, Yufang Jin, Wujie Wen, Caiwen Ding, Mimi Xie

Energy harvesting (EH) technology that harvests energy from ambient environment is a promising alternative to batteries for powering those devices due to the low maintenance cost and wide availability of the energy sources.

AutoML Model extraction

NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks

1 code implementation11 Jun 2022 Nuo Xu, Binghui Wang, Ran Ran, Wujie Wen, Parv Venkitasubramaniam

Membership inference attacks (MIAs) against machine learning models can lead to serious privacy risks for the training dataset used in the model training.

Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation

no code implementations27 Aug 2019 Xiaolong Ma, Geng Yuan, Sheng Lin, Caiwen Ding, Fuxun Yu, Tao Liu, Wujie Wen, Xiang Chen, Yanzhi Wang

To mitigate the challenges, the memristor crossbar array has emerged as an intrinsically suitable matrix computation and low-power acceleration framework for DNN applications.

Model Compression Quantization

Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds

no code implementations CVPR 2019 Zihao Liu, Xiaowei Xu, Tao Liu, Qi Liu, Yanzhi Wang, Yiyu Shi, Wujie Wen, Meiping Huang, Haiyun Yuan, Jian Zhuang

In this paper we will use deep learning based medical image segmentation as a vehicle and demonstrate that interestingly, machine and human view the compression quality differently.

Image Compression Image Segmentation +3

Progressive DNN Compression: A Key to Achieve Ultra-High Weight Pruning and Quantization Rates using ADMM

2 code implementations23 Mar 2019 Shaokai Ye, Xiaoyu Feng, Tianyun Zhang, Xiaolong Ma, Sheng Lin, Zhengang Li, Kaidi Xu, Wujie Wen, Sijia Liu, Jian Tang, Makan Fardad, Xue Lin, Yongpan Liu, Yanzhi Wang

A recent work developed a systematic frame-work of DNN weight pruning using the advanced optimization technique ADMM (Alternating Direction Methods of Multipliers), achieving one of state-of-art in weight pruning results.

Model Compression Quantization

E-RNN: Design Optimization for Efficient Recurrent Neural Networks in FPGAs

no code implementations12 Dec 2018 Zhe Li, Caiwen Ding, Siyue Wang, Wujie Wen, Youwei Zhuo, Chang Liu, Qinru Qiu, Wenyao Xu, Xue Lin, Xuehai Qian, Yanzhi Wang

It is a challenging task to have real-time, efficient, and accurate hardware RNN implementations because of the high sensitivity to imprecision accumulation and the requirement of special activation function implementations.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Defensive Dropout for Hardening Deep Neural Networks under Adversarial Attacks

no code implementations13 Sep 2018 Siyue Wang, Xiao Wang, Pu Zhao, Wujie Wen, David Kaeli, Peter Chin, Xue Lin

Based on the observations of the effect of test dropout rate on test accuracy and attack success rate, we propose a defensive dropout algorithm to determine an optimal test dropout rate given the neural network model and the attacker's strategy for generating adversarial examples. We also investigate the mechanism behind the outstanding defense effects achieved by the proposed defensive dropout.

A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers

3 code implementations ECCV 2018 Tianyun Zhang, Shaokai Ye, Kaiqi Zhang, Jian Tang, Wujie Wen, Makan Fardad, Yanzhi Wang

We first formulate the weight pruning problem of DNNs as a nonconvex optimization problem with combinatorial constraints specifying the sparsity requirements, and then adopt the ADMM framework for systematic weight pruning.

Image Classification Network Pruning

Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples

2 code implementations CVPR 2019 Zihao Liu, Qi Liu, Tao Liu, Nuo Xu, Xue Lin, Yanzhi Wang, Wujie Wen

Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently.

Classification General Classification +2

MT-Spike: A Multilayer Time-based Spiking Neuromorphic Architecture with Temporal Error Backpropagation

no code implementations14 Mar 2018 Tao Liu, Zihao Liu, Fuhong Lin, Yier Jin, Gang Quan, Wujie Wen

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 broad spectrum of recognition applications.

PT-Spike: A Precise-Time-Dependent Single Spike Neuromorphic Architecture with Efficient Supervised Learning

no code implementations14 Mar 2018 Tao Liu, Lei Jiang, Yier Jin, Gang Quan, Wujie Wen

One of the most exciting advancements in AI over the last decade is the wide adoption of ANNs, such as DNN and CNN, in many real-world applications.

DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Framework

no code implementations14 Mar 2018 Zihao Liu, Tao Liu, Wujie Wen, Lei Jiang, Jie Xu, Yanzhi Wang, Gang Quan

To reduce the data storage and transfer overhead in smart resource-limited Internet-of-Thing (IoT) systems, effective data compression is a "must-have" feature before transferring real-time produced dataset for training or classification.

Data Compression General Classification +2

Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks

no code implementations14 Feb 2018 Qi Liu, Tao Liu, Zihao Liu, Yanzhi Wang, Yier Jin, Wujie Wen

In this work, we for the first time investigate the multi-factor adversarial attack problem in practical model optimized deep learning systems by jointly considering the DNN model-reshaping (e. g. HashNet based deep compression) and the input perturbations.

Adversarial Attack

Cannot find the paper you are looking for? You can Submit a new open access paper.