Honghui Xu 许宏辉

Ph.D. Candidate

Georgia State University

Biography

Honghui Xu is a PhD student, advised by Dr. Cai and Dr. Li, in Department of Computer Science at Georgia State University (GSU). He received a Bachelor’s degree from University of Eletronic Science and Technology of China (UESTC), advised by Dr. Deng, Dr. Xu, Dr. Zhao, Dr. Xie, and Dr. Tian. His research focuses on machine learning and deep learning, including the fundamental theory of machine learning, the applications of deep learning in computer vision field, and the topic about privacy-preserving machine learning.

Download my resumé .

Interests

Fundamental Theory of Machine Learning
Applications of Deep Learning
Privacy-Preserving Machine Learning

Education

PhD in Computer Science, 2019-Present
Georgia State University
BSc in Computer Science, 2015-2019
University of Electronic Science and Technology of China

Featured Publications

Honghui Xu 许宏辉

September, 2022 Processing

Privacy-Preserving Multimodal Sentiment Analysis

We propose a Differentially Private Correlated Representation Learning (DPCRL) model to achieve privacy-preserving multimodal sentiment analysis by combining a correlated representation learning scheme with a differential privacy protection scheme.

Bingyi Xie, Honghui Xu 许宏辉, Zuobin Xiong, Yingshu Li, Zhipeng Cai

August, 2022 IEEE SmartData (Best Paper)

A Self-Supervised Purification Mechanism for Adversarial Samples

This paper proposes a purification mechanism that combines both adversarial training-based and input processing-based methods to defend the threats of adversarial samples.

Zhipeng Cai, Zuobin Xiong, Honghui Xu 许宏辉, Peng Wang, Wei Li, Yi Pan

April, 2021 CSUR (Impact Factor: 10.282)

Generative Adversarial Networks: A Survey Toward Private and Secure Applications

The existing works are classified into proper categories based on privacy and security functions, and this survey conducts a comprehensive analysis of their advantages and drawbacks.

Recent Publications

Quickly discover relevant content by filtering publications.

Honghui Xu 许宏辉 (2022). Privacy-Preserving Multimodal Sentiment Analysis. Processing.

Honghui Xu 许宏辉, Zhipeng Cai, Wei Li (2022). Privacy-Preserving Mechanisms for Multi-Label Image Recognition. TKDD (Impact Factor: 4.54).

PDF Cite Code

Bingyi Xie, Honghui Xu 许宏辉, Zuobin Xiong, Yingshu Li, Zhipeng Cai (2022). A Self-Supervised Purification Mechanism for Adversarial Samples. IEEE SmartData (Best Paper).

PDF Cite

Honghui Xu 许宏辉, Wei Li, Zhipeng Cai (2022). Analysis on methods to effectively improve transfer learning performance. TCS.

PDF Cite

Suparna De, Maria Bermudez-Edo, Honghui Xu 许宏辉, Zhipeng Cai (2022). Deep Generative Models in the Industrial Internet of Things: A Survey. TII (Impact Factor: 10.215).

PDF Cite

Honghui Xu 许宏辉, Zhipeng Cai, Ruinian Li, Wei Li (2022). Efficient CityCam-to-Edge Cooperative Learning for Vehicle Counting in ITS. TITS (Impact Factor: 2.534).

PDF Cite Code

Honghui Xu 许宏辉, Zhipeng Cai, Wei Li (2021). Which Option is a Better Way to Improve Transfer Learning Performance?. COCOA.

PDF Cite

Honghui Xu 许宏辉, Zhipeng Cai, Daniel Takabi, Wei Li (2021). Audio-Visual Autoencoding for Privacy-Preserving Video Streaming. IoTJ (Impact Factor: 9.936).

PDF Cite Code

Zhipeng Cai, Zuobin Xiong, Honghui Xu 许宏辉, Peng Wang, Wei Li, Yi Pan (2021). Generative Adversarial Networks: A Survey Toward Private and Secure Applications. CSUR (Impact Factor: 10.282).

PDF Cite

Zuobin Xiong, Honghui Xu 许宏辉, Zhipeng Cai, Wei Li (2021). Multi-Source Adversarial Sample Attack on Autonomous Vehicles. TVT (Impact Factor: 5.978).

PDF Cite

Research Experience

Undergraduate Research Assistant

Dr.Deng Yong’s Lab in Institution of Fundamental and Frontier Science (UESTC)

Sep 2016 – Jun 2017 Chengdu, China

Investigate some interesting topics about D-S evidence theory. The direction of determination is to solve the problem of fusion of related evidence sources.

Undergraduate Research Assistant

Dr.Xu Zenglin’s Lab in School of Computer Science and Engineering (UESTC)

Aug 2017 – Jun 2018 Chengdu China

Study the low-rank model with Dr.Kang Zhao. We improved the image classification algorithm based on the low-rank model.

Undergraduate Research Assistant

Future Media Lab in School of Computer Science and Engineering (UESTC)

Aug 2017 – Dec 2018 Chengdu China

Become a teaching assistant to go to Electronics Technology 29-th Institution of China to conduct Reinforcement Learning lectures.

Undergraduate Research Assistant

Dr.Ling Tian’s Lab in School of Computer Science and Engineering (UESTC)

Sep 2018 – May 2019 Chengdu China

Start the investigation about privacy-preserving machine learning.