/target_identification

CCS'22 Paper: "Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation"

Primary LanguagePythonMIT LicenseMIT

Target Identification and Renormalized Influence

docs

This repository contains the source code for reproducing the results of the CCS'22 paper "Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation".

Running the Program

Each task is divided into a different subprogram. Inside the corresponding source directory, call:

python driver.py ConfigFile

where ConfigFile is one of the yaml configuration files in folder configs.

Requirements

Our implementation was tested in Python 3.10.10. For the full requirements, see requirements.txt.

We recommend running our program in a virtual environment. Once your virtual environment is created and active, run the following in the src directory:

pip install --user --upgrade pip
pip install -r requirements.txt

License

MIT

Citation

@inproceedings{Hammoudeh:2022:TargetIdentification,
    author    = {Zayd Hammoudeh and
                 Daniel Lowd},
    title     = {Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation},
    booktitle = {Proceedings of the 2022 {ACM} {SIGSAC} Conference on Computer and Communications Security},
    series = {{CCS}’22},
    year = {2022},
}