Xiao Zhang

Email：xiao_zhang@hust.edu.cn

GitHub： https://github.com/ZhangXiao96

Web：https://zhangxiao96.github.io/

CSDN Blog (Chinese)：https://blog.csdn.net/z_x_1996

Education

2018-2021 M. Eng. School of Artificial Intelligence & Automation, HUST

2014-2018 B. Eng. School of Optical & Electronic Information, HUST

Research Interests

Generalization/Memorization in DNNs, Deep Learning, AI security, Brain-Computer Interfaces

Publications

  1. X. Zhang and D. Wu, “Empirical Studies on the Properties of Linear Regions in Deep Neural Networks,” in Proc. Int’l Conf. on Learning Representations (ICLR), Addis Ababa, Ethiopia, April 2020.
  2. X. Zhang and D. Wu, “Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs,” arXiv: 2004.13954, 2020.
  3. X. Zhang, D. Wu, L. Ding, H. Luo, C-T Lin, T-P Jung, R. Chavarriaga, “Tiny Noise Can Make an EEG-Based Brain-Computer Interface Speller Output Anything,” National Science Review, 2020, Major Revision.
  4. X. Zhang and D. Wu, “On the Vulnerability of CNN Classifiers in EEG-Based BCIs,” IEEE Trans. on Neural Systems and Rehabilitation Engineering, vol. 27, no. 5, pp. 814-825, 2019.
  5. Z. Liu*, X. Zhang*, D. Wu, “Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs,” IEEE Trans. on Human-Machine Systems, 2019, Major Revision.
  6. X. Jiang, X. Zhang, D. Wu, “Active Learning for Black-Box Adversarial Attacks in EEG-Based Brain-Computer Interfaces,” IEEE Symposium Series on Computational Intelligence, Xiamen, China, December 2019.

Awards

  1. 2020 Goodix Scholarship for Technology
  2. 2019 National Scholarship for Postgraduates
  3. 2019 1st Place – China Brain-Computer Interface Competition
  4. 2018 1st Place – IEEE WCCI Open Source Intelligence Discovery for Cybersecurity Threat
  5. 2018 3rd Place – Shenzhen International Competition for Medical and Health Big Data Innovative Application