I am a Ph.D. student at the Provable Responsible AI and Data Analytics (PRADA) Lab at the King Abdullah University of Science and Technology (KAUST), advised by Prof. Di Wang.

Before that, I was an algorithm engineer at the trustworthy AI research group at JD Explore Academy, JD.com, Inc. I received MPhil in Computer Science from The University of Sydney, advised by Prof. Dacheng Tao, and B.Sc in Mathematics from the South China University of Technology, advised by Prof. Chuhua Xian.

My research lies in trustworthy AI, especially the security and privacy aspects of machine learning. I am interested in using mathematical principles to identify and mitigate security and privacy risks in real-world machine learning systems.

Contact
shaopeng.fu@kaust.edu.sa
shaopengfu15@gmail.com

Pinned
PRADA Lab is looking for Postdocs/PhDs/Interns. Please checkout this page.

News

• 12/2023: I accepted the invitation to serve as a reviewer for ICML 2024.
• 10/2023: We released our new paper “Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach”.
• 09/2023: I accepted the invitation to serve as a reviewer for AISTATS 2024.
• 08/2023: I started my Ph.D. journey at the King Abdullah University of Science and Technology!
• 08/2023: I accepted the invitation to serve as a reviewer for ICLR 2024.
• 05/2023: I started a research internship at the PRADA Lab @ KAUST, hosted by Prof. Di Wang!
• 03/2023: I accepted the invitation to serve as a reviewer for NeurIPS 2023.
• 12/2022: I accepted the invitation to serve as a reviewer for ICML 2023.
• 07/2022: I accepted the invitation to serve as a reviewer for ICLR 2023.
• 03/2022: I accepted the invitation to serve as a reviewer for NeurIPS 2022.
• 01/2022: Two papers were accepted by ICLR 2022!

Publications [Google Scholar]

* indicates co-first authors.

• Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach [arXiv] [Code]
  Shaopeng Fu and Di Wang
  arXiv preprint 2023

• Robust Unlearnable Examples: Protecting Data Against Adversarial Learning [Link] [arXiv] [Video] [Code]
  Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen and Dacheng Tao
  ICLR 2022

• Knowledge Removal in Sampling-based Bayesian Inference [Link] [arXiv] [Video] [Code]
  Shaopeng Fu*, Fengxiang He* and Dacheng Tao
  ICLR 2022

• Artificial Neural Variability for Deep Learning: On Overfitting, Noise Memorization, and Catastrophic Forgetting [Link] [arXiv] [Code]
  Zeke Xie, Fengxiang He, Shaopeng Fu, Issei Sato, Dacheng Tao and Masashi Sugiyama
  Neural Computation 33 (8), 2021

• Robustness, Privacy, and Generalization of Adversarial Training [arXiv] [Code]
  Fengxiang He*, Shaopeng Fu*, Bohan Wang* and Dacheng Tao
  arXiv preprint 2020

Services

• Conference Reviewer
  • ICML (2022–2024), ICLR (2022–2024), NeurIPS (2021–2023), AISTATS (2021, 2024)
• Journal Reviewer
  • IEEE Transactions on Cybernetics
  • Neural Processing Letters

Selected Awards

• International Collegiate Programming Contest (ICPC)
  
  • The ICPC Asia-East Continent Final Xi’an Site, Silver Medal, 2018
  • The ICPC Asia Regional Contest Qingdao Site, Silver Medal, 2018
  • The ICPC Asia Regional Contest Shenyang Site, Gold Medal (Rank: 6/186), 2018
  • The ACM-ICPC Asia Regional Contest Xi’an Site, Silver Medal, 2017
• National Scholarship, Ministry of Education of P.R. China, 2017 & 2018