Yu LI 李渝


Ph.D.
Department of Computer Science and Engineering
The Chinese University of Hong Kong


Office: Rm1026, SHB, CHHK, Shatin, HongKong
Email: yuli@cse.cuhk.edu.hk
Google Scholar, DBLP


I have successfully defended my Ph.D. thesis 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. Before that, 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 interest lies in the intersection of computer security, machine learning, and software engineering, with a special emphasis on AI security and AI testing.

I am going to join HIT(SZ) as an assistant professor this year, cheers!

news

Mar 24, 2022 I have successfully defended my thesis!.
Sep 29, 2021 Our paper “TestRank: Bringing order into unlabeled test instances for deep learning tasks” has been accepted to [NeurIPS’21].
Feb 25, 2021 Our paper “AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference” has been accepted to DAC’21 with an acceptance rate of 23%.

selected publications

  1. ISSTA’22
    HybridRepair: Towards Annotation-Efficient Repair for Deep Learning Models
    Yu Li, Muxi Chen, and Xu, Qiang
    ISSTA 2022
  2. CCS’20
    DeepDyve: Dynamic Verification for Deep Neural Networks
    Li, Yu*, Li, Min*, Luo, Bo, Tian, Ye, and Xu, Qiang
    In Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security (CCS) 2020
  3. ACSAC’19
    D2NN: A Fine-Grained Dual Modular Redundancy Framework for Deep Neural Networks
    Li, Yu, Liu, Yannan, Li, Min, Tian, Ye, Luo, Bo, and Xu, Qiang
    In Proceedings of the 35th Annual Computer Security Applications Conference (ACSAC) 2019
  4. DAC’21
    AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference
    Li, Min, Li, Yu, Tian, Ye, Jiang, Li, and Xu, Qiang
    The Design Automation Conference (DAC) 2021
    arXiv
  5. IJCAI’21
    Information Bottleneck Approach to Spatial Attention Learning
    Lai, Qiuxia, Li, Yu, Zeng, Ailing, Liu, Minhao, Sun, Hanqiu, and Xu, Qiang
    International Joint Conference on Artificial Intelligence (IJCAI) 2021
    arXiv
  6. NeurIPS’21
    TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
    Li, Yu, LI, Min, Lai, Qiuxia, Liu, Yannan, and Xu, Qiang
    In Advances in Neural Information Processing Systems 2021