Towards Adversarial Evaluations of Inexact Machine Unlearning

Shashwat Goel, Ameya Prabhu, Sernam Lim, Phillip Torr, Amartya Sanyal, Ponnurangam Kumaraguru

This repository contains the code used in our experiments of our paper on Evaluating Machine Unlearning in the src/ folder along with some sample scripts in the scripts/ folder.

Citing this work

If you use this repository for academic research, you are encouraged to cite our paper:

@misc{goel2023adversarial,
      title={Towards Adversarial Evaluations for Inexact Machine Unlearning}, 
      author={Shashwat Goel and Ameya Prabhu and Amartya Sanyal and Ser-Nam Lim and Philip Torr and Ponnurangam Kumaraguru},
      year={2023},
      eprint={2201.06640},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}```