iamgroot42 / blackboxsok

Code for 'SoK: Pitfalls in Evaluating Black-Box Attacks' , SaTML 2024.

blackboxsok

Codebase for Sok: Pitfalls in Evaluating Black-Box Attacks.

Installing the package

1. Install any dependencies
2. Install the package via pip install -e . from the code/ folder.

Setting things up

Make sure you set the following paths:

export BLACKBOXSOK_DATA_PATH=/path/to/data
export BLACKBOXSOK_MODELS_PATH=/path/to/models
export BLACKBOXSOK_CACHE_PATH=/path/to/cache

Running experiments

Coming soon

Citation

If you use our repository/codebase for your experiments, please cite our work as:

@inproceedings{suya2024sok,
  title={Sok: Pitfalls in Evaluating Black-Box Attacks},
  author={Suya, Fnu and Suri, Anshuman and Zhang, Tingwei and Hong, Jingtao and Tian, Yuan and Evans, David},
  booktitle={IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)},
  year={2024}
}