Your enquiry has been successfully sent
Your enquiry could not be processed. Please contact us directly at www.csiro.au/Contact to make your enquiry
Biography
Hongsheng is currently a postdoctoral fellowship at Data61, CSIRO, Australia. His research focuses on AI privacy and security, especially membership inference attacks, differential privacy, and inference attacks in the context of federated learning. He has published several international refereed journal and conference papers, including ACM Computing Surveys, IJCAI, ICDM, and Asia CCS.
Other Interests
Selected Publications:
2023
Zhibo Zhu, Zhiyu Jin, Hongsheng Hu, Jason Xue, and Huaming Chen. "ML-Compass: A Comprehensive Assessment Framework for Machine Learning Models", In Proceedings of the 2023 ACM on Asia Conference on Computer and Communications Security, 2023.
2022
Hu, Hongsheng, Zoran Salcic, Gillian Dobbie, Jinjun Chen, Lichao Sun, and Xuyun Zhang. "Membership inference via backdooring." In The 31st International Joint Conference on Artificial Intelligence (IJCAI-22). 2022.
Hu, Hongsheng, Zoran Salcic, Lichao Sun, Gillian Dobbie, Philip S. Yu, and Xuyun Zhang. "Membership inference attacks on machine learning: A survey." ACM Computing Surveys (CSUR) 54, no. 11s (2022): 1-37.
Xiang, Haolong, Hongsheng Hu, and Xuyun Zhang. "DeepiForest: A Deep Anomaly Detection Framework with Hashing Based Isolation Forest." In 2022 IEEE International Conference on Data Mining (ICDM), pp. 1251-1256. IEEE, 2022.
2021
Hu, Hongsheng, Zoran Salcic, Lichao Sun, Gillian Dobbie, and Xuyun Zhang. "Source inference attacks in federated learning." In 2021 IEEE International Conference on Data Mining (ICDM), pp. 1102-1107. IEEE, 2021.
Academic Qualifications
-
2022
PhD, Electrical and Computer Engineering
The University of Auckland
Current Roles
-
CERC Postdoctoral Fellow
Cybersecurity and Quantum Systems Group, CSIRO's Data61
Professional Experiences
-
2017-2018
Visting Student
The University of Calgary