Li Yu (李渝)
Scholar

Li Yu (李渝)

Google Scholar ID: M0zhrM8AAAAJ
The Chinese University of Hong Kong
AI SecurityLLM/VLM SecHardware Testing & SecurityReliable Autonomous Driving
Citations & Impact
All-time
Citations
680
 
H-index
13
 
i10-index
16
 
Publications
20
 
Co-authors
10
list available
Publications
20 items
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
  • - August 2025, three papers accepted to NeurIPS 2025.
  • - August 2025, four papers accepted to TDSC 2025, TIFS 2025, TCAD, and ASE 2025.
  • - May 2025, paper on safety-critical driving dataset generation published.
  • - May 2025, two papers accepted by ACL 2025.
  • - May 2025, one paper accepted by ICML 2025.
  • - January 2025, one paper accepted by ICLR 2025.
  • - December 2024, one paper accepted by AAAI 2025.
  • - September 2024, two papers accepted by NeurIPS 2024.
  • - 2023, HiBug: On Human Interpretable Model Debug, NeurIPS 2023.
  • - 2022, HybridRepair: Towards Annotation-Efficient Repair for Deep Learning Models, ISSTA 2022.
  • - 2020, DeepDyve: Dynamic Verification for Deep Neural Networks, CCS 2020.
  • - 2019, D2NN: A Fine-Grained Dual Modular Redundancy Framework for Deep Neural Networks, ACSAC 2019.
  • - 2021, TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks, NeurIPS 2021.
  • - 2021, AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference, DAC 2021.
  • - 2021, Information Bottleneck Approach to Spatial Attention Learning, IJCAI 2021.
Research Experience
  • - ZJU100 Professor at the School of Integrated Circuits, Zhejiang University
Education
  • - Ph.D. from The Chinese University of Hong Kong, supervised by Prof. Qiang Xu
  • - Master's degree (Cum Laude) from KU Leuven, supervised by Prof. Erik Jan Marinissen and Prof. Hailong Jiao
  • - Bachelor of Science and Bachelor of Engineering degrees with honor from KU Leuven and UESTC, respectively
Background
  • Research interests include: Security of LLM/VLM (including jailbreak, privacy, and watermark techniques), safety of autonomous driving systems, hardware and software co-design.
Miscellany
  • Looking for multiple self-motivated Ph.D. students, master students, and research assistants. Welcome to contact via Email: li.yu@zju.edu.cn. More information on the Chinese website.