Awni Hannun


Privacy Preserving Machine Learning

The focus of this work is learning models while keeping the data and/or the learned models private.

Selected Publications
  • Measuring Data Leakage in Machine-Learning Models with Fisher Information Awni Hannun, Chuan Guo, Laurens van der Maaten. UAI 2021. (paper, code, slides)
    Best Paper at UAI 2021
  • Secure multiparty computations in floating-point arithmetic Chuan Guo, Awni Hannun, Brian Knott, Laurens van der Maaten, Mark Tygert, Ruiyu Zhu. Information and Inference, 2021. (paper, code)
  • Data Appraisal Without Data Sharing Mimee Xu, Laurens van der Maaten, Awni Hannun. NeurIPS PPML Workshop, 2020. (paper)
  • The Trade-Offs of Private Prediction Laurens van der Maaten*, Awni Hannun*. arXiv:2007.05089, 2020. (paper, code)
  • Certified Data Removal from Machine Learning Models Chuan Guo, Tom Goldstein, Awni Hannun, Laurens van der Maaten. ICML 2020. (paper, code)
  • Privacy-Preserving Multi-Party Contextual Bandits Awni Hannun, Brian Knott, Shubho Sengupta, Laurens van der Maaten. arXiv:1910.05299 2019. (paper, code)