anand-vishwakarma-1 / differential_privacy

Differential Privacy: The right tool against training-data Reconstruction Attack

Differential Privacy: The right tool against training-data Reconstruction Attack

Trained models and extraction

You can download all the 6 trained models and extraction models of each from this Google Drive Link.

BibTeX

@inproceedings{haim2022reconstructing,
 author = {Haim, Niv and Vardi, Gal and Yehudai, Gilad and Shamir, Ohad and Irani, Michal},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Koyejo and S. Mohamed and A. Agarwal and D. Belgrave and K. Cho and A. Oh},
 pages = {22911--22924},
 publisher = {Curran Associates, Inc.},
 title = {Reconstructing Training Data From Trained Neural Networks},
 url = {https://proceedings.neurips.cc/paper_files/paper/2022/file/906927370cbeb537781100623cca6fa6-Paper-Conference.pdf},
 volume = {35},
 year = {2022}
}