Hongsheng Hu
Scholar

Hongsheng Hu

Google Scholar ID: 2VU5HJIAAAAJ
Lecturer, School of Information and Physical Sciences, University of Newcastle
Trustworthy Machine LearningMachine Unlearning
Citations & Impact
All-time
Citations
1,390
 
H-index
12
 
i10-index
15
 
Publications
20
 
Co-authors
4
list available
Resume (English only)
Academic Achievements
  • Published in top venues including S&P, NDSS, USENIX Security, NeurIPS, IJCAI, AAAI, WWW, ICDM, ACM CSUR, TDSC.
  • 17 conference papers and 6 journal articles.
  • Notable publications:
  • - 'When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning' (ACM CCS 2025)
  • - 'A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services' (NDSS 2024)
  • - 'DNN-GP: Diagnosing and Mitigating Model's Faults Using Latent Concepts' (USENIX Security 2024)
Background
  • Currently Lecturer at the School of Information and Physical Sciences, The University of Newcastle, Australia.
  • Research focuses on enhancing the trustworthiness of machine learning systems by identifying critical privacy vulnerabilities and developing robust defensive strategies.
  • Key research areas: Data Privacy, Machine Unlearning, Trustworthy Machine Learning.
  • Serves as Program Committee member for top-tier conferences including USENIX Security, NDSS, ICLR, IJCAI, WWW, ICDM, ECML, PKDD, etc.
  • Regular reviewer for prestigious journals such as TIFS, TDSC, IEEE IPAMI, ACM CSUR, TKDE, Computer & Security.