ZHU Yulin (Tony)

• Postdoctoral Fellow
• Department of Computing, The Hong Kong Polytechnic University
• VA315, The Hong Kong Polytechnic University
  Hung Hom, Kowloon, Hong Kong SAR, China
• Email: yulinzhu@polyu.edu.hk; zhuyulin.tony@gmail.com

Biography

Yulin Zhu is a postdoc in the Department of Computing at The Hong Kong Polytechnic University, supervised by Prof. Kai Zhou. He obtained his B.S. from Wuhan University and Ph.D. from The Chinese University of Hong Kong advised by Prof. Xiaodan FAN. His research interests include AI security, data security and privacy, adversarial machine learning and adversarial network analysis.

Professional Experience

• 07/2022 - Now, Postdoctoral Fellow, The Hong Kong Polytechnic University, Hong Kong
• 10/2020 - 06/2022, Research Assistant, The Hong Kong Polytechnic University, Hong Kong
• 01/2020 - 08/2020, Part-time Research Intern, TCL Moka International Limited, Hong Kong

Education

• 09/2016 - 12/2020, Ph.D., The Chinese University of Hong Kong
• 09/2012 - 06/2016, B.S., Wuhan University

Selected Publications (More in Google Scholar)

• [IEEE S&P] Node-aware Bi-smoothing: Certified Robustness against Graph Injection Attacks
  Yuni Lai, Yulin Zhu, Bailin Pan, Kai Zhou
  IEEE Symposium on Security and Privacy 2024, (CCF-A, Core-A*)
• [TIFS] Towards Secrecy-Aware Attacks Against Trust Prediction in Signed Social Networks (Code)
  Yulin Zhu, Tomasz Michalak, Xiapu Luo, Xiaoge Zhang, Kai Zhou
  IEEE Transactions on Information Forensics and Security, January 2024, (CCF-A, Core-A)
• [ICASSP] Cost Aware Untargeted Poisoning Attack Against Graph Neural Networks
  Yuwei Han, Yuni Lai, Yulin Zhu, Kai Zhou
  2024 IEEE International Conference on Acoustics, Speech and Signal Processing, April 2024, (CCF-B, Core-B)
• [ICASSP] Uncovering Strong Ties: A Study of Indirect Sybil Attack on Signed Social Network
  Yu Bu, Yulin Zhu, Longling Geng, Kai Zhou
  2024 IEEE International Conference on Acoustics, Speech and Signal Processing, April 2024, (CCF-B, Core-B)
• [ICDE] Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
  Xing Ai, Jialong Zhou, Yulin Zhu, Gaolei Li, Tomasz P Michalak, Xiapu Luo, Kai Zhou
  40th International Conference on Data Engineering, May 2024, (CCF-A, Core-A*)
• [TIFS] Towards Adversarially Robust Recommendation from Adaptive Fraudster Detection
  Yuni Lai, Yulin Zhu, Wenqi Fan, Xiaoge Zhang, Kai Zhou
  IEEE Transactions on Information Forensics and Security, October 2023, (CCF-A, Core-A)
• [TKDE] FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification (Code)
  Yulin Zhu, Liang Tong, Gaolei Li, Xiapu Luo, Kai Zhou
  IEEE Transactions on Knowledge and Data Engineering, October 2023, (CCF-A, Core-A*)
• [ICDE] BinarizedAttack: Structural Poisoning Attacks to Graph-Based Anomaly Detection (Code)
  Yulin Zhu, Yuni Lai, Kaifa Zhao, Xiapu Luo, Mingquan Yuan, Jian Ren, and Kai Zhou
  38th International Conference on Data Engineering, May 2022, (CCF-A, Core-A*)
• [CCS] Structural Attack Against Graph Based Android Malware Detection
  Kaifa Zhao, Hao Zhou, Yulin Zhu, Xian Zhan, Kai Zhou, Jianfeng Li, Le Yu, Wei Yuan, Xiapu Luo
  Proceedings of ACM Conference on Computer and Communications Security, November 2021, (CCF-A, Core-A*)
• [ICDM] Attacking Similarity-Based Sign Prediction
  MT Godziszewski, TP Michalak, M Waniek, T Rahwan, Kai Zhou, Yulin Zhu
  21st IEEE International Conference on Data Mining, December 2021, (CCF-B, Core-A*)

Recent Preprints/Under Review

• From Bi-Level to One-Level: A Framework for Structural Attacks to Graph Anomaly Detection
  Yulin Zhu, Yuni Lai, Kaifa Zhao, Xiapu Luo, Mingquan Yuan, Jun Wu, Jian Ren, Kai Zhou
  Arxiv 2206.08260, 2022. (Arxiv)
• Simple yet Effective Gradient-Free Graph Convolutional Networks
  Yulin Zhu, Xing Ai, Qimai Li, Xiao-Ming Wu, Kai Zhou
  Arxiv 2302.00371, 2023. (Arxiv)
• Homophily-Driven Sanitation View for Robust Graph Contrastive Learning
  Yulin Zhu, Xing Ai, Yevgeniy Vorobeychik, Kai Zhou
  Arxiv 2307.12555, 2023. (Arxiv)
• Coupled-Space Attacks against Random-Walk-based Anomaly Detection
  Yuni Lai, Marcin Waniek, Liying Li, Jingwen Wu, Yulin Zhu, Tomasz P. Michalak, Talal Rahwan, Kai Zhou
  Arxiv 2307.14387, 2023. (Arxiv)
• Unleashing the Power of Indirect Attacks against Trust Prediction via Preferential Path
  Yu Bu, Yulin Zhu, Longling Geng, Kai Zhou
• Universally Robust Graph Neural Networks by Preserving Neighbor Similarity
  Yulin Zhu, Yuni Lai, Xing Ai, Kai Zhou
  Arxiv 2401.09754, 2024. (Arxiv)

Teaching Experience

• Introduction to Statistics (STAT1011), Teaching Assistant, STAT, CUHK
• Basic Methods in Biomedical Statistics (STAT3004), Teaching Assistant, STAT, CUHK
• Statistical Techniques in Life Science (STAT3210), Teaching Assistant, STAT, CUHK
• Statistics Projects (STAT4011), Teaching Assistant, STAT, CUHK

Community Service

• Subreviewer: CIKM-2022, AAMAS-2022, AAMAS-2023, AAMAS-2024, ECAI-2023, CIKM-2023, SecureComm-2023.
• External Reviewer: KDD-2022.
• Reviewer: IET Communications, TDSC, TKDD, IoTJ, KDD-2024.
• PC Member: AAAI-2023, AAAI-2024.

Invited Talks

• 07/12/2022 Invited talk titled “BinarizedAttack: Structural Poisoning Attacks to Graph-Based Anomaly Detection” hosted by Shanghai Jiao Tong University, Institute of Cyber Science and Technology.