Skip to content

HKU IDS Scholar

Home
Professor Ho CHEN
Chair Professor
HKU Musketeers Foundation Institute of Data Science and
Department of Computer Science, School of Computing and Data Science, HKU 
chenho@hku.hk (852) 3910 2338
P307H, Graduate House, HKU
About Me
Professor Chen received his PhD in Computer Science at the University of California, Berkeley. His current research interests are computer security, machine learning, and program analysis and testing. He directs the JC STEM Lab of Intelligent Cybersecurity. He is a fellow of IEEE.
Current Research Project
Professor Chen focuses on AI-driven security and the security of AI. He is exploring innovative applications of machine learning models and algorithms to security problems, such as program analysis, automatic program testing (fuzzing), and anomaly detection at the enterprise scale. He is also working on the robustness and explainability of machine learning models.
Selected Publications
  1. He, Y., Huang, J., Rong, Y., Guo, Y., Wang, E. & Chen, H. “UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing.” International Symposium on Software Testing and Analysis (ISSTA), .
  2. Lyu, Y., Xie, Y., Chen, P. & Chen, H. “Prompt Fuzzing for Fuzz Driver Generation.” ACM Conference on Computer and Communications Security (CCS), 
  3. Li, Q., Guo, Y., Zuo, W. & Chen, H. “Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly.” Neural Information Processing Systems (NeurIPS), 
  4. Li, Q., Guo, Y., Zuo, W. & Chen, H. “Improving Adversarial Transferability via Intermediate-level Perturbation Decay.” Neural Information Processing Systems (NeurIPS), .
  5. Chen, P., Xie, Y., Lyu, Y., Wang, Y. & Chen, H. “HOPPER: Interpretative Fuzzing for Libraries” ACM Conference on Computer and Communications Security (CCS), .
  6. Zhao, J., Rong, Y., Guo, Y., He, Y. & Chen, H. “Understanding Programs by Exploiting (Fuzzing) Test Cases.” Findings of the Association for Computational Linguistics (ACL), 
  7. Li, Q., Guo, Y., Zuo, W. & Chen, H. “Squeeze Training for Adversarial Robustness.” International Conference on Learning Representations (ICLR), .
  8. Li, Q., Guo, Y., Zuo, W. & Chen, H. “Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.” International Conference on Learning Representations (ICLR), .
  9. Chen, P. & Chen, H. “Angora: Efficient Fuzzing by Principled Search.” IEEE Symposium on Security & Privacy, .
  10. Meng, D. & Chen, H. “MagNet: a Two-Pronged Defense Against Adversarial Examples.”ACM Conference on Computer and Communications Security (CCS), .
Research Interests
Computer Security, Machine Learning, Program Analysis and Testing
Seminar