I am now an assistant professor at the School of Software Technology at Zhejiang University. Before that, I was a postdoctoral scholar at the Penn State University working under Prof. Ting Wang.

I obtained my Ph.D. degree in the College of Computer Science and Technology at the Zhejiang University in 2022, supervised by Prof. Shouling Ji. During Ph.D., I have spent wonderful times in collaborating with academics at the university (e.g., Prof. Bo Li at UIUC, and Prof. Ting Wang at PSU), and researchers in the industrial community (e.g., Dr. Tao Wei at Baidu USA (now Ant Financial), Dr. Jie Shi at Huawei Singapore Research Center). Before that, I obtained my B.E. degree in the Communication Engineering at the College of Information Science and Techonology, Xiamen University.

My current research interests include trustworthy large language models and LLM-based agent safety. I have published 20+ papers at the top international conferences and journals such as USENIX Security, CCS, NDSS, ICLR, NeurIPS, ICCV, TDSC, etc.

Openings: I am looking for motivated PhD/Master/intern students to join my research group. Please drop me an email if you are interested in working with me!

πŸ”₯ News

  • 2024.05: Β  πŸŽ‰ Two papers were accepted by ACL 2024.
  • 2024.01: Β  πŸŽ‰ One paper was accepted by ICLR 2024.
  • 2023.09: Β  πŸŽ‰ Three papers were accepted by NeurIPS 2023.
  • 2023.07: Β  πŸŽ‰ One paper was accepted by ICCV 2023.
  • 2023.06: Β  I will join the School of Software Technology at Zhejiang University as an Assistant Professor in Aug 2023!
  • 2023.06: Β  I was invited to serve as a reviewer for EMNLP 2023.
  • 2023.05: Β  πŸŽ‰ One paper was accepted by USENIX Security 2023.
  • 2023.04: Β  I was invited to serve as a reviewer for Cybersecurity.
  • 2023.01: Β  I was invited to serve as a PC member for ACL 2023.
  • 2022.08: Β  Join College of Information Sciences and Technology, Penn State University as a postdoctoral scholar.

πŸ“ Conference Publications

CCS 2021

Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networks

Tianyu Du, Shouling Ji, Lujia Shen, Yao Zhang, Jinfeng Li, Jie Shi, Chengfang Fang, Jianwei Yin, Raheem Beyah, Ting Wang

  • This work proposes Cert-RNN, a general framework for certifying the robustness of RNNs.
USENIX Security 2021

TextShield: Robust Text Classification Based on Multimodal Embedding and Neural Machine Translation

Jinfeng Li*, Tianyu Du*, Shouling Ji, Rong Zhang, Quan Lu, Min Yang, and Ting Wang (*Co-first authors)

  • This work proposes TextShield, a new adversarial defense framework specifically designed for Chinese deep learning-based text classification models.
NDSS 2019

TextBugger: Generating Adversarial Text Against Real-world Applications Jinfeng Li, Shouling Ji, Tianyu Du, Bo Li, and Ting Wang

  • This work proposes TextBugger, a general attack framework for generating adversarial texts.

πŸ“ Journal Publications

🧾 Poster

πŸ“– arXiv

πŸ““ Patents

  • CN, β€œA method and system for generating adversarial audio under white-box settings”

πŸ’» Experience

  • 2022.08 - 2023.08, Postdoctoral Scholar, Penn State University.
  • 2017.03 - 2018.03, Research Scientist Intern, Alibaba, Hangzhou.

πŸŽ“ Education

  • 2017.09 - 2022.06, Ph.D., Cyber Security, Zhejiang University, Hangzhou.
  • 2013.09 - 2017.06, B.E., Communication Engineering, Xiamen University, Xiamen.

πŸ‘©β€πŸ« Service

πŸ’¬ Invited Talks

  • 2021.07, Adversarial attack and defense in the natural language procesing domain, G.O.S.S.I.P Summer School, Shanghai.

πŸŽ– Honors and Awards

  • 2019.12 Inscrypt 2019 Best Paper Award
  • 2018.10 Guanglianda Second Prize Scholarship
  • 2014.10 National Scholarship (Undergraduate) (Top 1%)