Yu LI

I am a tenure-track Assistant Professor of Computer Science and Technology Department, Harbin Institute of Technology (Shenzhen). Before that, I obtained my Ph.D. degree at The Chinese University of Hong Kong (Shatin, N.T., Hong Kong) under the supervision of Prof.Qiang Xu. I received my Master degree with Cum Laude in 2017 from Katholieke Universiteit Leuven (KU Leuven, Leuven, Belgium), under the supervision of Prof.Erik Jan Marinissen and Prof.Hailong Jiao. I received the Bachelor of Science and Bachelor of Engineering degrees with honor in 2016 from both KU Leuven and University of Electronic Science and Technology of China (UESTC, Chengdu, China), respectively.

Currently, my research interests include:

  • Secure and Reliable Machine Learning, including explainability, adversarial attacks, and defenses on large language/vision/multi-modal models.
  • High-Reliability Hardware, including fault injection attacks, side-channel, etc.

I am looking for multiple self-motivated Ph.D. students, master students, and research assistants. Welcome to contact me via Email li.yu@hit.edu.cn.

News

2024-09 Two papers have been accepted by NeurIPS 2024!
2024-08 I will serve as a reviewer and PC member for AAAI 2025 and ICLR 2025; consider submitting papers!
2024-07 I will serve as a PC member for IEEE EuroS&P 2025; consider submitting papers!
2024-05 I will serve as a PC member for ACSAC 2024; consider submitting papers!
2024-05 One paper has been accepted to ICML'24.
2024-04 One paper has been accepted to IJCAI'24.
2023-12 Our paper "HiBug: On Human Interpretable Model Debug" has been accepted to NeurIPS'23.
2023-10 One paper has been accepted to ITC'23.
2022-03 I have successfully defended my thesis!

Selected Publications [ Full List ]

  1. NeurIPS’23
    HiBug: On Human Interpretable Model Debug
    Muxi Chen*, Yu Li*, and Qiang Xu
    Conference on Neural Information Processing Systems, (NeurIPS), 2023.
  2. ISSTA’22
    HybridRepair: Towards Annotation-Efficient Repair for Deep Learning Models
    Yu Li, Muxi Chen, and Qiang Xu
    The ACM SIGSOFT International Symposium on Software Testing and Analysis, (ISSTA), 2022.
  3. CCS’20
    DeepDyve: Dynamic Verification for Deep Neural Networks
    Yu Li*, Min Li*, Bo Luo, Ye Tian, and Qiang Xu
    ACM SIGSAC Conference on Computer and Communications Security, (CCS), 2020.
  4. ACSAC’19
    D2NN: A Fine-Grained Dual Modular Redundancy Framework for Deep Neural Networks
    Yu Li, Yannan Liu, Min Li, Ye Tian, Bo Luo, and Qiang Xu
    Annual Computer Security Applications Conference, (ACSAC), 2019.
  5. NeurIPS’21
    TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
    Yu Li, Min Li, Qiuxia Lai, Yannan Liu, and Qiang Xu
    Conference on Neural Information Processing Systems, (NeurIPS), 2021.
  6. DAC’21
    AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
    Min Li, Yu Li, Ye Tian, Li Jiang, and Qiang Xu
    The Design Automation Conference, (DAC), 2021.
  7. IJCAI’21
    Information Bottleneck Approach to Spatial Attention Learning
    Qiuxia Lai, Yu Li, Ailing Zeng, Minhao Liu, Hanqiu Sun, and Qiang Xu
    International Joint Conference on Artificial Intelligence, (IJCAI), 2021.

Teaching

  1. COMP5034
    System Security, 2023 Fall
  2. COMP3054
    Computers and Network Security, 2023 Spring
  3. CSCI3250
    Computers and Society (with Prof. CHAU Chuck-jee)
  4. CENG2400
    Embedded System Design (with Prof. Qiang Xu)
  5. ENGG1100
    Introduction to Engineering Design (with Prof. Anthony SUM)