Privacy-Enhanced Zero-Shot Learning via Data-Free Knowledge Transfer

Rui Gao, Fan Wan, Daniel Organisciak, Jiyao Pu, Haoran Duan, Peng Zhang, Xingsong Hou, Yang Long

Abstract

Considering the increasing concerns about data copyright and sensitivity issues, we present a novel Privacy-Enhanced Zero-Shot Learning (PE-ZSL) paradigm. The key innovation is to involve a teacher model as the data safeguard to guide the PE-ZSL model training without data sharing. The PE-ZSL model consists of a generator and student network, which can achieve data-free knowledge transfer while maintaining the performance of teacher model. We investigate ‘black-’ and ‘white-box’ scenarios in PE-ZSL task as different levels of framework privacy. Besides, we provide the discussion of teacher model in both omniscient and quasi-omniscient settings according to the knowledge space. Despite simple implementations and data-missing disadvantages, our PE-ZSL framework can retain state-of-the-art ZSL and GZSL performance under the ‘white-box’ scenario. Extensive qualitative and quantitative analysis also demonstrates promising results when deploying the model under ‘black-box’ scenario.
BibTeX
@inproceedings{gao2023privacy,
  author = {Rui Gao and Fan Wan and Daniel Organisciak and Jiyao Pu and Haoran Duan and Peng Zhang and Xingsong Hou and Yang Long},
  title = {{Privacy-Enhanced Zero-Shot Learning via Data-Free Knowledge Transfer}},
  booktitle = {ICME},
  year = {2023},
  doi = {10.1109/icme55011.2023.00081},
}

Loading related content...

Figure