The Education University of Hong Kong (EdUHK)
ORCID: 0000-0001-5966-1338
Research Interests
Software Engineering
Software Testing
Program Analysis
Deep Learning Testing
AI in Education
SE4AI
AI4SE
Deep Learning Compilation
Blockchain Security
Professional Affiliations
- B.Eng. in Data and Computer Science, Sun Yat-Sen University
- Ph.D. in Computer Science, City University of Hong Kong
- Postdoctoral Fellow, Faculty of Engineering, The University of Hong Kong
- Assistant Professor, Department of Mathematics and Information Technology, The Education University of Hong Kong
Academic Honors
- editorial_profile_page.no_data
Professional Experience
editorial_profile_page.no_data
Biography
Zhengyuan (Jankin) Wei is currently an assistant professor with Department of Mathematics and Information Technology, The Education University of Hong Kong. Prior that, he worked as a postdoctoral researcher at Faculty of Engineering of The University of Hong Kong. He obtained his Ph.D. degree in Computer Science from City University of Hong Kong in 2023 and his B.Eng. degree in Data and Computer Science from Sun Yat-Sen University in 2017. His research interests primarily revolve around software engineering, with a current emphasis on the testing aspects of artificial intelligence (SE4AI & AI4SE).
Awards & Recognition
- editorial_profile_page.no_data
Publications & Representative Works
Complete Bibliography
2024
CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models
2024
Introduction to Teaching and Learning with Chatbots Powered by Student-In-the-Loop Knowledge Bases
2023
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models
2023
DeepPatch: Maintaining Deep Learning Model Programs to Retain Standard Accuracy with Substantial Robustness Improvement
2022
A modular software engineering toolbox for deep learning models
2022
Predictive mutation analysis of test case prioritization for deep neural networks
2021
Fuzzing deep learning models against natural robustness with filter coverage
ACM Transactions on Software Engineering and Methodology
