|
I am a second-year Ph.D. student of INSC at Tsinghua University since 09/2023. Contact: dongjs23@mails.tsinghua.edu.cn |
|
|
| 08/23/2025 | One paper got accepted to EMNLP 2025 main (oral)! |
| 08/10/2025 | I created a new website for my research! |
|
|
|
|
Jianshuo Dong, Yutong Zhang, Yan Liu, Zhenyu Zhong, Tao Wei, Ke Xu, Minlie Huang, Chao Zhang, Han Qiu PDF / Code / Oral TL;DR: Diving into the internals to understand LLMs' prompt leakage intents. |
|
|
Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang, Tianwei Zhang, Hao Wang, Hewu Li, Qi Li, Chao Zhang, Ke Xu, Han Qiu PDF / Code / Poster TL;DR: An inference cost attack targeting modern auto-regressive LLMs. |
|
|
Jianshuo Dong, Han Qiu, Yiming Li, Tianwei Zhang, Yuanjie Li, Zeqi Lai, Chao Zhang, Shu-Tao Xia PDF / Code / Poster TL;DR: Insert unactivated backdoor in the model training process and make it activated by bit-flip attack. |
|
|
|
|
Jianshuo Dong, Yujia Fu, Chuanrui Hu, Chao Zhang, Han Qiu arXiv / Code TL;DR: Does reasoning models have human-like cognitive habits? |
|
|
Jianshuo Dong, Tianyi Zhang, Feng Yan, Yuanjie Li, Hewu Li, Han Qiu arXiv TL;DR: Evaluate and improve the performance of LLMs in automatically refining cellular network specifications concerning security/trustworthiness issues. |
|
|
| 2019-2023 | Wuhan University, Wuhan, China |
| 2023-2028 (expected) | Tsinghua University, Beijing, China |
|
|
| 2025 Spring | Trustworthy Machine Learning, Tsinghua University, Teaching Assistant |
|
|
|
|
Reviewer |
|
|
Notable Reviewer |