郑华伟

我是郑华伟，目前为浙江大学软件工程硕士研究生，导师为邓达臻老师，预计 2027 年毕业。

我的主要研究方向是数据智能体（Data Agents）与可信大语言模型，在大模型安全、数据智能体系统，以及面向复杂数据的检索与推理等方面积累了研究与工程实践经验。

研究之外，我喜欢电影、剧集、阅读、音乐、历史、科技和游戏，尤其是能带来启发或沉浸体验的作品。成功只有一个——按照自己的方式，去度过人生。——《明朝那些事儿》

你可以通过 zhenghuawei [at] zju.edu.cn 联系我，也可以在 GitHub 和 Google Scholar 查看我的更多工作。

动态

2026.04.07	一篇论文被 ACL 2026 Main 接收。
2026.01.18	一篇论文被 CHI 2026 接收。
2024.08.15	我们的论文 “AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow” 获得 IEEE VIS 2024 Best Paper Honorable Mention。

代表论文

ACL

StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

Huawei Zheng, Xinqi Jiang, Sen Yang, Shouling Ji, Yingcai Wu, and Dazhen Deng

ACL 2026 Main (CCF-A)

PDF ACL Code BibTeX

@inproceedings{zheng-etal-2026-stealthgraph,
  title = {{StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation}},
  author = {Zheng, Huawei and Jiang, Xinqi and Yang, Sen and Ji, Shouling and Wu, Yingcai and Deng, Dazhen},
  booktitle = {Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)},
  year = {2026},
  url = {https://aclanthology.org/2026.acl-long.295/},
  pages = {6519--6539},
}

CHI

NoteFlow: Leveraging Charts as Sight Glasses for Consistent and Continuous Data Flow Tracing

Yuan Tian, Dazhen Deng, Sen Yang, Huawei Zheng, Bowen Shi, Kai Xiong, Xinjing Yi, and Yingcai Wu

CHI 2026 (CCF-A)

PDF DOI Code BibTeX

@inproceedings{10.1145/3772318.3790356,
  title = {{NoteFlow: Leveraging Charts as Sight Glasses for Consistent and Continuous Data Flow Tracing}},
  author = {Tian, Yuan and Deng, Dazhen and Yang, Sen and Zheng, Huawei and Shi, Bowen and Xiong, Kai and Yi, Xinjing and Wu, Yingcai},
  booktitle = {Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems},
  year = {2026},
  doi = {10.1145/3772318.3790356},
  url = {https://doi.org/10.1145/3772318.3790356},
  numpages = {17},
}

VIS

AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow

Dazhen Deng, Chuhan Zhang, Huawei Zheng, Yuwen Pu, Shouling Ji, and Yingcai Wu

IEEE Transactions on Visualization and Computer Graphics (IEEE VIS 2024), vol. 31, no. 1, pp. 492-502, Jan. 2025 (CCF-A, JCR-Q1)

Best Paper Honorable Mention Award

PDF Demo VIS BibTeX

@article{10681029,
  title = {{AdversaFlow: Visual Red Teaming for Large Language Models with Multi-Level Adversarial Flow}},
  author = {Deng, Dazhen and Zhang, Chuhan and Zheng, Huawei and Pu, Yuwen and Ji, Shouling and Wu, Yingcai},
  journal = {IEEE Transactions on Visualization and Computer Graphics},
  year = {2024},
  volume = {31},
  number = {1},
  pages = {492-502},
  url = {https://ieeexplore.ieee.org/document/10681029/},
}