Zihao Zhu

zihaozhu@link.cuhk.edu.cn
Hi, this is Zihao Zhu (朱梓豪). I am currently a Ph.D. student in Data Science at The Chinese University of Hong Kong, Shenzhen, under the supervision of Prof. Baoyuan Wu. Previously, I received my Master’s degree from the Institute of Information Engineering at the University of Chinese Academy of Sciences in 2021.
My research interests broadly span the field of AI security, with a particular focus on the following areas:
- Safety of Large Language Models: I study the safety challenges associated with large language models (LLMs), including jailbreak attacks and safety alignment, aiming to enhance the robustness and reliability of LLMs without compromising their utility.
- Data Safety in AI Systems: Data is the fuel of AI. I investigate various aspects of data safety in Data-centric AI (DCAI), with particular emphasis on backdoor attacks and data quality assessment.
- Safety in Embodied AI: I explore safety concerns in embodied AI systems, focusing on risk assessment for embodied AI agents. This emerging area is crucial as AI systems become more integrated into physical environments.
I am currently on the job market and seeking full-time opportunities in academia or industry. I would be delighted to connect if you have relevant openings or suggestions.
news
May 19, 2025 | Our paper “BlackboxBench: A Comprehensive Benchmark of Black-box Adversarial Attacks” has been accepted to IEEE TPAMI! ![]() |
---|---|
Mar 29, 2025 | Our paper “BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning” has been accepted to IJCV! ![]() |
Feb 19, 2025 | Our new paper “BoT: Breaking Long Thought Processes of o1-like Large Language Models through Backdoor Attack” is available on arXiv. Check out the code on GitHub. |
Dec 07, 2024 | One new preprint is available: “HMGIE: Hierarchical and Multi-Grained Inconsistency Evaluation for Vision-Language Data Cleansing” |
Jan 20, 2024 | Our paper “Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning” has been accepted to AAAI 2024! |