title: mithridatium
authors:
  - given-names: Pelumi
    family-names: Oluwategbe
    email: pelumi.oluwategbe@slu.edu
    affiliation: Saint Louis University
  - given-names: William
    family-names: Phoenix
    email: will.phoenix@slu.edu
    affiliation: Saint Louis University
  - given-names: Gustavo
    family-names: Lucca
    email: gustavo.lucca@slu.edu
    affiliation: Saint Louis University
  - given-names: Payton
    family-names: Guffey
    email: payton.guffey@slu.edu
    affiliation: Saint Louis University
cff-version: 1.2.0
message: If you use this software, please cite it using the metadata from this file.
type: software
abstract: Mithridatium is a research-driven project aimed at detecting backdoors
  and data poisoning in downloaded pretrained models or pipelines (e.g., from
  Hugging Face).   Our goal is to provide a modular, command-line tool that
  helps researchers and engineers trust the models they use.
keywords:
  - data privacy
  - machine-learning
  - python
  - security
license: MIT-Modern-Variant
repository-code: https://github.com/oss-slu/mithridatium