128 citations · 331 across the 14 of their papers we have counts for
14 papers
Toward Robust Spiking Neural Network Against Adversarial Perturbation
Ling Liang, Kaidi Xu, Xing Hu +2
As spiking neural networks (SNNs) are deployed increasingly in real-world efficiency critical applications, the security concerns in SNNs attract more attention. Currently, researc…
ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
Husheng Han, Kaidi Xu, Xing Hu +6
Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or defor…
Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment
Jiaming Guo, Rui Zhang, Xishan Zhang +6
Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied…
Rubik: A Hierarchical Architecture for Efficient Graph Learning
Xiaobing Chen, Yuke Wang, Xinfeng Xie +9
Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce,…
SEALing Neural Network Models in Secure Deep Learning Accelerators
Pengfei Zuo, Yu Hua, Ling Liang +3
Deep learning (DL) accelerators are increasingly deployed on edge devices to support fast local inferences. However, they suffer from a new security problem, i.e., being vulnerable…
HyGCN: A GCN Accelerator with Hybrid Architecture
Mingyu Yan, Lei Deng, Xing Hu +6
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU. Guided by the characterization, we design a GCN accelerator, HyGCN, using a hybrid arch…
Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
Ling Liang, Xing Hu, Lei Deng +5
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models ac…
Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
Lei Deng, Yujie Wu, Yifan Hu +6
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with h…
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
Xing Hu, Ling Liang, Lei Deng +7
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject. Even those that dep…
FPSA: A Full System Stack Solution for Reconfigurable ReRAM-based NN Accelerator Architecture
Yu Ji, Youyang Zhang, Xinfeng Xie +5
Neural Network (NN) accelerators with emerging ReRAM (resistive random access memory) technologies have been investigated as one of the promising solutions to address the \textit{m…
Programmable Neural Network Trojan for Pre-Trained Feature Extractor
Yu Ji, Zixin Liu, Xing Hu +2
Neural network (NN) trojaning attack is an emerging and important attack model that can broadly damage the system deployed with NN models. Existing studies have explored the outsou…
Batch Normalization Sampling
Zhaodong Chen, Lei Deng, Guoqi Li +4
Deep Neural Networks (DNNs) thrive in recent years in which Batch Normalization (BN) plays an indispensable role. However, it has been observed that BN is costly due to the reducti…
Dynamic Sparse Graph for Efficient Deep Learning
Liu Liu, Lei Deng, Xing Hu +4
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference…
Crossbar-aware neural network pruning
Ling Liang, Lei Deng, Yueling Zeng +5
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operati…