Personal Profile
Chen Hongrui is a master's student in computer science at The Chinese University of Hong Kong, Shenzhen. He possesses an interdisciplinary background in applied mathematics, data science, and computer science. He has long been deeply involved in the fields of artificial intelligence security, backdoor learning, computer vision, and generative models, engaging in related research and engineering practice.
The research focuses on constructing an evaluation system for backdoor learning algorithms and exploring universal backdoor attack methods for generative image editing. It possesses comprehensive research capabilities, spanning from abstracting scientific research problems, designing and implementing algorithms, to building open-source platforms. Relevant research findings have been published in top conferences and journals in the field of artificial intelligence, such as NeurIPS, TPAMI, and IJCV. The backdoor learning benchmark platform he led in building has garnered widespread academic attention
Educational Background
September 2022 – November 2025
The Chinese University of Hong Kong, Shenzhen
Computer Science, Master's Degree Candidate
September 2020 – July 2022
The Chinese University of Hong Kong, Shenzhen
Data Science, Master of Science
September 2016 – July 2020
The Chinese University of Hong Kong, Shenzhen
Bachelor of Science in Applied Mathematics
Work Experience
September 2021 - June 2022 Shenzhen Big Data Research Institute Research Assistant
Academic papers
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning，NeurIPS 2022
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning，IJCV 2025
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers，TPAMI
Representative achievements
Method and system for generating poisoned images in backdoor attacks, and backdoor attack method, published in June 2023, patent number: CN116309920A