Corpus ID: 235212189

Fooling Partial Dependence via Data Poisoning

@article{Baniecki2021FoolingPD,
  title={Fooling Partial Dependence via Data Poisoning},
  author={Hubert Baniecki and Wojciech Kretowicz and P. Biecek},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.12837}
}
Many methods have been developed to understand complex predictive models and high expectations are placed on post-hoc model explainability. It turns out that such explanations are not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be manipulated in an adversarial manner, which is… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 49 REFERENCES
Interpretable Deep Learning under Fire
Underspecification Presents Challenges for Credibility in Modern Machine Learning
Fooling Neural Network Interpretations via Adversarial Model Manipulation
Evaluating Explanation Methods for Deep Learning in Security
DALEX: Explainers for Complex Predictive Models in R
  • P. Biecek
  • Computer Science
  • J. Mach. Learn. Res.
  • 2018
pdp: An R Package for Constructing Partial Dependence Plots
Interpretation of Neural Networks is Fragile
...
1
2
3
4
5
...