Biography

I am a fourth-year PhD at University of Auckland, Faculty of Engineering. My research focus on AI privacy and security, especially membership inference attacks, differential privacy, and inference attacks in the context of federated learning.

Interests
  • Privacy and Security in Machine Learning
  • Membership Inference Attacks
  • Federated Learning
Education

  • PhD in Computer Systems Engineering, 2022

    University of Auckland, New Zealand

  • BSc in Mathematics and Statistics, 2018

    University of Calgary, Canada

  • BSc in Mathematics and Applied Mathematics, 2018

    China University of Petroleum (East China), China

Publications

Quickly discover relevant content by filtering publications.
Hongsheng Hu, Zoran Salcic, Lichao Sun, Gillian Dobbie, Philip S. Yu, Xuyun Zhang (2022). Membership Inference Attacks on Machine Learning: A Survey. ACM Computing Surveys.

PDF Cite Code

Hongsheng Hu, Zoran Salcic, Gillian Dobbie, Jinjun Chen, Lichao Sun, Xuyun Zhang (2022). Membership Inference via Backdooring. 2022 International Joint Conference on Artificial Intelligence (IJCAI).

PDF Cite Code

Hongsheng Hu, Zoran Salcic, Lichao Sun, Gillian Dobbie, Xuyun Zhang (2021). Source Inference Attacks in Federated Learning. 2021 IEEE International Conference on Data Mining (ICDM).

PDF Cite Code

Hongsheng Hu, Zoran Salcic, Gillian Dobbie, Yi Chen, Xuyun Zhang (2021). EAR: An Enhanced Adversarial Regularization Approach against Membership Inference Attacks. 2021 International Joint Conference on Neural Networks (IJCNN).

PDF Cite

Meng Liu, Hongsheng Hu, Haolong Xiang, Chi Yang, Lingjuan Lyu, Xuyun Zhang (2021). Clustering-based Efficient Privacy-preserving Face Recognition Scheme without Compromising Accuracy. ACM Transactions on Sensor Networks.

PDF Cite

Hongsheng Hu, Gillian Dobbie, Zoran Salcic, Meng Liu, Jianbing Zhang, Xuyun Zhang (2020). A Locality Sensitive Hashing Based Approach for Federated Recommender System. 2020 20th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGRID).

PDF Cite

Contact