Manipulating SHAP via Adversarial Data Perturbations (Student Abstract)

Authors

  • Hubert Baniecki Faculty of Mathematics and Information Science, Warsaw University of Technology
  • Przemyslaw Biecek Faculty of Mathematics and Information Science, Warsaw University of Technology

DOI:

https://doi.org/10.1609/aaai.v36i11.21590

Keywords:

Explainability, Interpretability, Adversarial Attack, Responsible AI, Tabular Data

Abstract

We introduce a model-agnostic algorithm for manipulating SHapley Additive exPlanations (SHAP) with perturbation of tabular data. It is evaluated on predictive tasks from healthcare and financial domains to illustrate how crucial is the context of data distribution in interpreting machine learning models. Our method supports checking the stability of the explanations used by various stakeholders apparent in the domain of responsible AI; moreover, the result highlights the explanations' vulnerability that can be exploited by an adversary.
AAAI-22 Proceedings Cover

Downloads

Published

2022-06-28

How to Cite

Baniecki, H., & Biecek, P. (2022). Manipulating SHAP via Adversarial Data Perturbations (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12907-12908. https://doi.org/10.1609/aaai.v36i11.21590

Issue

Vol. 36 No. 11: IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations

Section

AAAI Student Abstract and Poster Program