R-GAP
Recursive Gradient Attack on Privacy
Description:
We provide a closed-form recursive procedure to recover data from gradients in deep neural networks. We name it Recursive Gradient Attack on Privacy (R-GAP)
More Information:
- Grand Challenge/Workpackage(s): GC1 - WP5
- Responsible Research Lead: Matthew Blaschko
- Authors: Junyi Zhu
- Programming Language: Python
- Link to the repository
- Categories: Images, Networks and graphs
Publications:
- J. Zhu, M. Blaschko, "R-GAP: Recursive Gradient Attack on Privacy", in Proceedings of the International Conference on Learning Representations, 2021.
