Yuyi Zhong's homepage

The simple personal webpage!

View the Project on GitHub JacksonZyy/homepage

Welcome to the homepage of Yuyi Zhong

My name is Yuyi, and I am a Ph.D. candidate at School of Computing, National University of Singapore (NUS). Currently, I am under the supervision of Associate Professor KHOO Siau Cheng to analyze and verify the safety and security of neural networks.

Previously, I obtained my B.Sc. from Huazhong University of Science and Technology (HUST), China in 2018 where I worked in software security including vulnerability detection.

I can be reached at: yuyizhong@comp.nus.edu.sg.

Research

My research interests lie in applying formal methods used in program analysis to neural network verification. Currently, I am focusing on a research project of building a configurable neural network verification platform that enables quick and systematic construction and experimentation of network analyses. To do so, we first build a verification tool BBPoly that enables fast but efficient network verification with limited computational resources. Our second work constructs a verification method ARENA that conducts both robustness verification and falsification effectively and efficiently. The third work focuses on a pre-processing technique REDNet before the verification process, which generates a reduced network that helps accelerate the subsequent verification. My current ongoing work is optimization-based network verification on GPU, in collaboration with Dr. Hanping Xu and Shaun Tan.

For more details about my research and publications, please check my CV.

Conference Papers

  1. Expediting Neural Network Verification via Network Reduction
    • Yuyi Zhong*, Ruiwei Wang*, Siau-Cheng Khoo
    • * means equal contribution
    • IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023
  2. ARENA: Enhancing Abstract Refinement for Neural Network Verification
    • Yuyi Zhong, Quang-Trung Ta, Siau-Cheng Khoo
    • International Conference on Verification, Model Checking, and Abstract Interpretation (VMCAI), 2023
  3. Scalable and Modular Robustness Analysis of Deep Neural Networks
    • Yuyi Zhong, Quang-Trung Ta, Tianzuo Luo, Fanlong Zhang, Siau-Cheng Khoo
    • Asian Symposium on Programming Languages and Systems (APLAS), 2021
  4. SCVD: A New Semantics-Based Approach for Cloned Vulnerable Code Detection
    • Deqing Zou, Hanchao Qi, Zhen Li, Song Wu, Hai Jin, Guozhong Sun, Sujuan Wang, Yuyi Zhong
    • International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment (DIMVA), 2017
  5. VulDeePecker: A Deep Learning-Based System for Vulnerability Detection
    • Zhen Li, Deqing Zou, Shouhuai Xu, Xinyu Ou, Hai Jin, Sujuan Wang, Zhijun Deng, Yuyi Zhong
    • Annual Network and Distributed System Security Symposium (NDSS), 2018

Teaching and Grading

GitHub Repositories