Search Results for author: Zhi Zhang

Found 40 papers, 17 papers with code

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

no code implementations6 Sep 2022 Hua Ma, Yinshan Li, Yansong Gao, Zhi Zhang, Alsharif Abuadbba, Anmin Fu, Said F. Al-Sarawi, Nepal Surya, Derek Abbott

We observe that the backdoor effect of both misclassification and the cloaking are robustly achieved in the wild when the backdoor is activated with inconspicuously natural physical triggers.

Event Detection Image Classification +3

AI Enlightens Wireless Communication: A Transformer Backbone for CSI Feedback

no code implementations16 Jun 2022 Han Xiao, Zhiqin Wang, Dexin Li, Wenqiang Tian, Xiaofeng Liu, Wendong Liu, Shi Jin, Jia Shen, Zhi Zhang, Ning Yang

This paper is based on the background of the 2nd Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AIWork Group, where the framework of the eigenvector-based channel state information (CSI) feedback problem is firstly provided.

Data Augmentation

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

no code implementations31 May 2022 Shang Wang, Yansong Gao, Anmin Fu, Zhi Zhang, Yuqing Zhang, Willy Susilo

Both data are samples with triggers: the cover/poisoned data from non-source/source class(es) holds ground-truth/target labels.

Towards A Critical Evaluation of Robustness for Deep Learning Backdoor Countermeasures

no code implementations13 Apr 2022 Huming Qiu, Hua Ma, Zhi Zhang, Alsharif Abuadbba, Wei Kang, Anmin Fu, Yansong Gao

Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models.

Deep AutoAugment

1 code implementation11 Mar 2022 Yu Zheng, Zhi Zhang, Shen Yan, Mi Zhang

In this work, instead of fixing a set of hand-picked default augmentations alongside the searched data augmentations, we propose a fully automated approach for data augmentation search named Deep AutoAugment (DeepAA).

AutoML Data Augmentation +1

PPA: Preference Profiling Attack Against Federated Learning

no code implementations10 Feb 2022 Chunyi Zhou, Yansong Gao, Anmin Fu, Kai Chen, Zhiyang Dai, Zhi Zhang, Minhui Xue, Yuqing Zhang

By observing a user model's gradient sensitivity to a class, PPA can profile the sample proportion of the class in the user's local dataset, and thus the user's preference of the class is exposed.

Federated Learning Inference Attack

NTD: Non-Transferability Enabled Backdoor Detection

no code implementations22 Nov 2021 Yinshan Li, Hua Ma, Zhi Zhang, Yansong Gao, Alsharif Abuadbba, Anmin Fu, Yifeng Zheng, Said F. Al-Sarawi, Derek Abbott

A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments.

Face Recognition Traffic Sign Recognition

Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory

no code implementations ICLR 2022 Zhi Zhang, Zhuoran Yang, Han Liu, Pratap Tokekar, Furong Huang

This paper proposes a new algorithm for learning the optimal policies under a novel multi-agent predictive state representation reinforcement learning model.

reinforcement-learning

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

no code implementations7 Sep 2021 Zhi Zhang, Sheng-hua Zhong, Yan Liu

Data augmentation has recently achieved considerable performance improvement for deep learning models: increased accuracy, stability, and reduced over-fitting.

Data Augmentation EEG +2

AI Enlightens Wireless Communication: Analyses, Solutions and Opportunities on CSI Feedback

no code implementations12 Jun 2021 Han Xiao, Zhiqin Wang, Wenqiang Tian, Xiaofeng Liu, Wendong Liu, Shi Jin, Jia Shen, Zhi Zhang, Ning Yang

In this paper, we give a systematic description of the 1st Wireless Communication Artificial Intelligence (AI) Competition (WAIC) which is hosted by IMT-2020(5G) Promotion Group 5G+AI Work Group.

Quantization

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

no code implementations9 May 2021 Huming Qiu, Hua Ma, Zhi Zhang, Yifeng Zheng, Anmin Fu, Pan Zhou, Yansong Gao, Derek Abbott, Said F. Al-Sarawi

To this end, a 1-bit quantized DNN model or deep binary neural network maximizes the memory efficiency, where each parameter in a BNN model has only 1-bit.

Quantization

Attention in Attention Network for Image Super-Resolution

2 code implementations19 Apr 2021 Haoyu Chen, Jinjin Gu, Zhi Zhang

In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial.

Image Super-Resolution Single Image Super Resolution

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

1 code implementation3 Mar 2021 Yansong Gao, Minki Kim, Chandra Thapa, Sharif Abuadbba, Zhi Zhang, Seyit A. Camtepe, Hyoungshick Kim, Surya Nepal

Federated learning (FL) and split learning (SL) are state-of-the-art distributed machine learning techniques to enable machine learning training without accessing raw data on clients or end devices.

BIG-bench Machine Learning Federated Learning

CrossNorm and SelfNorm for Generalization under Distribution Shifts

1 code implementation ICCV 2021 Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris Metaxas

Can we develop new normalization methods to improve generalization robustness under distribution shifts?

Unity of Opposites: SelfNorm and CrossNorm for Model Robustness

no code implementations1 Jan 2021 Zhiqiang Tang, Yunhe Gao, Yi Zhu, Zhi Zhang, Mu Li, Dimitris N. Metaxas

CrossNorm exchanges styles between feature channels to perform style augmentation, diversifying the content and style mixtures.

Object Recognition Unity

Insight-HXMT observations of Swift J0243.6+6124: the evolution of RMS pulse fractions at super-Eddington luminosity

no code implementations24 Dec 2020 P. J. Wang, L. D. Kong, S. Zhang, Y. P. Chen, S. N. Zhang, J. L. Qu, L. Ji, L. Tao, M. Y. Ge, F. J. Lu, L. Chen, L. M. Song, T. P. Li, Y. P. Xu, X. L. Cao, Y. Chen, C. Z. Liu, Q. C. Bu, C. Cai, Z. Chang, G. Chen, T. X. Chen, Y. B. Chen, W. Cui, W. W. Cui, J. K. Deng, Y. W. Dong, Y. Y. Du, M. X. Fu, G. H. Gao, H. Gao, M. Gao, Y. D. Gu, J. Guan, C. C. Guo, D. W. Han, Y. Huang, J. Huo, S. M. Jia, L. H. Jiang, W. C. Jiang, J. Jin, Y. J. Jin, B. Li, C. K. Li, G. Li, M. S. Li, W. Li, X. Li, X. B. Li, X. F. Li, Y. G. Li, Z. W. Li, X. H. Liang, J. Y. Liao, B. S. Liu, G. Q. Liu, H. W. Liu, X. J. Liu, Y. N. Liu, B. Lu, X. F. Lu, Q. Luo, T. Luo, X. Ma, B. Meng, Y. Nang, J. Y. Nie, G. Ou, N. Sai, R. C. Shang, X. Y. Song, L. Sun, Y. Tan, Y. L. Tuo, C. Wang, G. F. Wang, J. Wang, L. J. Wang, W. S. Wang, Y. S. Wang, X. Y. Wen, B. Y. Wu, B. B. Wu, M. Wu, G. C. Xiao, S. Xiao, S. L. Xiong, J. W. Yang, S. Yang, Yan Ji Yang, Yi Jung Yang, Q. B. Yi, Q. Q. Yin, Y. You, A. M. Zhang, C. M. Zhang, F. Zhang, H. M. Zhang, J. Zhang, T. Zhang, W. C. Zhang, W. Zhang, W. Z. Zhang, Y. F. Zhang, Y. J. Zhang, Y. Zhang, Zhao Zhang, Zhi Zhang, Z. L. Zhang, H. S. Zhao, X. F. Zhao, S. J. Zheng, Y. G. Zheng, D. K. Zhou, J. F. Zhou, Y. X. Zhu, Y. Zhu, R. L. Zhuang

The results show a general trend of the pulse fraction increasing with luminosity and energy at super-critical luminosity.

High Energy Astrophysical Phenomena

Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

1 code implementation21 Jul 2020 Yansong Gao, Bao Gia Doan, Zhi Zhang, Siqi Ma, Jiliang Zhang, Anmin Fu, Surya Nepal, Hyoungshick Kim

We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor. Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks.

Improving Semantic Segmentation via Self-Training

no code implementations30 Apr 2020 Yi Zhu, Zhongyue Zhang, Chongruo wu, Zhi Zhang, Tong He, Hang Zhang, R. Manmatha, Mu Li, Alexander Smola

In the case of semantic segmentation, this means that large amounts of pixelwise annotations are required to learn accurate models.

Domain Generalization Semantic Segmentation

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

no code implementations23 Sep 2019 Zhi Zhang, Jiachen Yang, Hongyuan Zha

Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions.

Multi-agent Reinforcement Learning reinforcement-learning

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

4 code implementations9 Jul 2019 Jian Guo, He He, Tong He, Leonard Lausen, Mu Li, Haibin Lin, Xingjian Shi, Chenguang Wang, Junyuan Xie, Sheng Zha, Aston Zhang, Hang Zhang, Zhi Zhang, Zhongyue Zhang, Shuai Zheng, Yi Zhu

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).

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

2 code implementations26 Apr 2019 Haibin Lin, Hang Zhang, Yifei Ma, Tong He, Zhi Zhang, Sheng Zha, Mu Li

One difficulty we observe is that the noise in the stochastic momentum estimation is accumulated over time and will have delayed effects when the batch size changes.

Image Classification object-detection +2

Bag of Tricks for Image Classification with Convolutional Neural Networks

25 code implementations CVPR 2019 Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

Much of the recent progress made in image classification research can be credited to training procedure refinements, such as changes in data augmentations and optimization methods.

Classification General Classification +5

Progressive Neural Networks for Image Classification

no code implementations25 Apr 2018 Zhi Zhang, Guanghan Ning, Yigang Cen, Yang Li, Zhiqun Zhao, Hao Sun, Zhihai He

The inference structures and computational complexity of existing deep neural networks, once trained, are fixed and remain the same for all test images.

Classification General Classification +1

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

no code implementations20 Feb 2018 Zhi Zhang, Yueqiang Cheng, Surya Nepal, Dongxi Liu, Qingni Shen, Fethi Rabhi

In this paper, we propose a reliable and practical system, named KASR, which transparently reduces attack surfaces of commodity OS kernels at runtime without requiring their source code.

Cryptography and Security Operating Systems

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

no code implementations20 Feb 2018 Yueqiang Cheng, Zhi Zhang, Surya Nepal, Zhi Wang

The exploit is motivated by our key observation that the modern OSes have double-owned kernel buffers (e. g., video buffers) owned concurrently by the kernel and user domains.

Cryptography and Security

Knowledge Projection for Deep Neural Networks

no code implementations26 Oct 2017 Zhi Zhang, Guanghan Ning, Zhihai He

In this paper, we will develop a new framework for training deep neural networks on datasets with limited labeled samples using cross-network knowledge projection which is able to improve the network performance while reducing the overall computational complexity significantly.

Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation

1 code implementation5 May 2017 Guanghan Ning, Zhi Zhang, Zhihai He

Human pose estimation using deep neural networks aims to map input images with large variations into multiple body keypoints which must satisfy a set of geometric constraints and inter-dependency imposed by the human body model.

Pose Estimation

Spatially Supervised Recurrent Convolutional Neural Networks for Visual Object Tracking

2 code implementations19 Jul 2016 Guanghan Ning, Zhi Zhang, Chen Huang, Zhihai He, Xiaobo Ren, Haohong Wang

In this paper, we develop a new approach of spatially supervised recurrent convolutional neural networks for visual object tracking.

object-detection Object Detection +1

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