b'Zhi Zhang'

research

∙ 09/21/2023

DeepTheft: Stealing DNN Model Architectures through Power Side Channel

Deep Neural Network (DNN) models are often deployed in resource-sharing ...

0 Yansong Gao, et al. ∙

research

∙ 07/12/2023

GLA-GCN: Global-local Adaptive Graph Convolutional Network for 3D Human

3D human pose estimation has been researched for decades with promising ...

0 Bruce X. B. Yu, et al. ∙

research

∙ 02/17/2023

CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension

The task of multimodal referring expression comprehension (REC), aiming ...

0 Zhi Zhang, et al. ∙

research

∙ 02/09/2023

Imperceptible Sample-Specific Backdoor to DNN with Denoising Autoencoder

The backdoor attack poses a new security threat to deep neural networks....

0 Jiliang Zhang, et al. ∙

research

∙ 09/06/2022

MACAB: Model-Agnostic Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World

Object detection is the foundation of various critical computer-vision t...

1 Hua Ma, et al. ∙

research

∙ 07/19/2022

MUD-PQFed: Towards Malicious User Detection in Privacy-Preserving Quantized Federated Learning

Federated Learning (FL), a distributed machine learning paradigm, has be...

0 Hua Ma, et al. ∙

research

∙ 05/31/2022

CASSOCK: Viable Backdoor Attacks against DNN in The Wall of Source-Specific Backdoor Defences

Backdoor attacks have been a critical threat to deep neural network (DNN...

0 Shang Wang, et al. ∙

research

∙ 03/29/2022

Systematically Evaluation of Challenge Obfuscated APUFs

As a well-known physical unclonable function that can provide huge numbe...

0 Yansong Gao, et al. ∙

research

∙ 03/24/2022

BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training

Multiple datasets and open challenges for object detection have been int...

5 Likun Cai, et al. ∙

research

∙ 02/10/2022

PPA: Preference Profiling Attack Against Federated Learning

Federated learning (FL) trains a global model across a number of decentr...

0 Chunyi Zhou, et al. ∙

research

∙ 01/21/2022

Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World

Deep learning models have been shown to be vulnerable to recent backdoor...

1 Hua Ma, et al. ∙

research

∙ 01/09/2022

A Retrospective and Futurespective of Rowhammer Attacks and Defenses on DRAM

Rowhammer has drawn much attention from both academia and industry in th...

0 Zhi Zhang, et al. ∙

research

∙ 11/22/2021

NTD: Non-Transferability Enabled Backdoor Detection

A backdoor deep learning (DL) model behaves normally upon clean inputs b...

5 Yinshan Li, et al. ∙

research

∙ 10/03/2021

Design and Evaluate Recomposited OR-AND-XOR-PUF

Physical Unclonable Function (PUF) is a hardware security primitive with...

0 Jianrong Yao, et al. ∙

research

∙ 09/07/2021

GANSER: A Self-supervised Data Augmentation Framework for EEG-based Emotion Recognition

The data scarcity problem in Electroencephalography (EEG) based affectiv...

11 Zhi Zhang, et al. ∙

research

∙ 08/20/2021

Quantization Backdoors to Deep Learning Models

There is currently a burgeoning demand for deploying deep learning (DL) ...

38 Hua Ma, et al. ∙

research

∙ 08/12/2021

Progressive Coordinate Transforms for Monocular 3D Object Detection

Recognizing and localizing objects in the 3D space is a crucial ability ...

3 Li Wang, et al. ∙

research

∙ 05/09/2021

RBNN: Memory-Efficient Reconfigurable Deep Binary Neural Network with IP Protection for Internet of Things

Though deep neural network models exhibit outstanding performance for va...

5 Huming Qiu, et al. ∙

research

∙ 04/19/2021

Attention in Attention Network for Image Super-Resolution

Convolutional neural networks have allowed remarkable advances in single...

10 Haoyu Chen, et al. ∙

research

∙ 03/03/2021

Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things

Federated learning (FL) and split learning (SL) are state-of-the-art dis...

0 Yansong Gao, et al. ∙

research

∙ 02/20/2021

SoftTRR: Protect Page Tables Against RowHammer Attacks using Software-only Target Row Refresh

Rowhammer attacks that corrupt level-1 page tables to gain kernel privil...

0 Zhi Zhang, et al. ∙

research

∙ 02/04/2021

SelfNorm and CrossNorm for Out-of-Distribution Robustness

Normalization techniques are crucial in stabilizing and accelerating the...

12 Zhiqiang Tang, et al. ∙

research

∙ 09/14/2020

AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results

This paper reviews the video extreme super-resolution challenge associat...

9 Dario Fuoli, et al. ∙

research

∙ 07/21/2020

Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

This work provides the community with a timely comprehensive review of b...

44 Yansong Gao, et al. ∙

research

∙ 07/17/2020

PThammer: Cross-User-Kernel-Boundary Rowhammer through Implicit Accesses

Rowhammer is a hardware vulnerability in DRAM memory, where repeated acc...

0 Zhi Zhang, et al. ∙

research

∙ 04/30/2020

Improving Semantic Segmentation via Self-Training

Deep learning usually achieves the best results with complete supervisio...

8 Yi Zhu, et al. ∙

research

∙ 04/19/2020

ResNeSt: Split-Attention Networks

While image classification models have recently continued to advance, mo...

16 Hang Zhang, et al. ∙

research

∙ 04/05/2020

DRAMDig: A Knowledge-assisted Tool to Uncover DRAM Address Mapping

As recently emerged rowhammer exploits require undocumented DRAM address...

0 Minghua Wang, et al. ∙

research

∙ 02/03/2020

GhostKnight: Breaching Data Integrity via Speculative Execution

Existing speculative execution attacks are limited to breaching confiden...

0 Zhi Zhang, et al. ∙

research

∙ 12/06/2019

TeleHammer : A Stealthy Cross-Boundary Rowhammer Technique

Rowhammer exploits frequently access specific DRAM rows (i.e., hammer ro...

0 Zhi Zhang, et al. ∙

research

∙ 11/23/2019

Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural Networks

This work corroborates a run-time Trojan detection method exploiting STR...

0 Yansong Gao, et al. ∙

research

∙ 10/21/2019

PiBooster: A Light-Weight Approach to Performance Improvements in Page Table Management for Paravirtual Virtual-Machines

In paravirtualization, the page table management components of the guest...

0 Zhi Zhang, et al. ∙

research

∙ 09/23/2019

Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization

Traffic congestion in metropolitan areas is a world-wide problem that ca...

2 Zhi Zhang, et al. ∙

research

∙ 07/09/2019

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer...

5 Jian Guo, et al. ∙

research

∙ 04/26/2019

Dynamic Mini-batch SGD for Elastic Distributed Training: Learning in the Limbo of Resources

With an increasing demand for training powers for deep learning algorith...

12 Haibin Lin, et al. ∙

research

∙ 04/16/2019

Just-in-Time Dynamic-Batching

Batching is an essential technique to improve computation efficiency in ...

0 Sheng Zha, et al. ∙

research

∙ 02/11/2019

Bag of Freebies for Training Object Detection Neural Networks

Comparing with enormous research achievements targeting better image cla...

2 Zhi Zhang, et al. ∙

research

∙ 12/04/2018

Bag of Tricks for Image Classification with Convolutional Neural Networks

Much of the recent progress made in image classification research can be...

18 Junyuan Xie, et al. ∙

research

∙ 04/25/2018

Progressive Neural Networks for Image Classification

The inference structures and computational complexity of existing deep n...

0 Zhi Zhang, et al. ∙

research

∙ 02/20/2018

KASR: A Reliable and Practical Approach to Attack Surface Reduction of Commodity OS Kernels

Commodity OS kernels have broad attack surfaces due to the large code ba...

0 Zhi Zhang, et al. ∙

research

∙ 02/20/2018

A Reliable and Practical Approach to Kernel Attack Surface Reduction of Commodity OS

Commodity OS kernels are known to have broad attack surfaces due to the ...

0 Zhi Zhang, et al. ∙

research

∙ 02/20/2018

Still Hammerable and Exploitable: on the Effectiveness of Software-only Physical Kernel Isolation

All the state-of-the-art rowhammer attacks can break the MMU-enforced in...

0 Yueqiang Cheng, et al. ∙

research

∙ 10/26/2017

Knowledge Projection for Deep Neural Networks

While deeper and wider neural networks are actively pushing the performa...

0 Zhi Zhang, et al. ∙

research

∙ 05/05/2017

Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

Human pose estimation using deep neural networks aims to map input image...

0 Guanghan Ning, et al. ∙

Zhi Zhang

Featured Co-authors