# SHAP-based Explanations are Sensitive to Feature Representation

arXiv: https://arxiv.org/abs/2505.08345 · HTML: https://mlsanity.com/paper/2505.08345/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 42 references that are in the map.
- First posted on arXiv 13 May 2025.

## Builds on (most cited first, 11 of 11)

- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [Explainable Machine Learning in Deployment](https://mlsanity.com/paper/1909.06342/) (2019)
- [Aequitas: A Bias and Fairness Audit Toolkit](https://mlsanity.com/paper/1811.05577/) (2018)
- [The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons](https://mlsanity.com/paper/1912.04930/) (2019)
- [Principles and Practice of Explainable Machine Learning](https://mlsanity.com/paper/2009.11698/) (2020)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [Racial categories in machine learning](https://mlsanity.com/paper/1811.11668/) (2018)
- [Rational Shapley Values](https://mlsanity.com/paper/2106.10191/) (2021)
- [A Critical Survey on Fairness Benefits of Explainable AI](https://mlsanity.com/paper/2310.13007/) (2023)
- [Epistemic values in feature importance methods: Lessons from feminist epistemology](https://mlsanity.com/paper/2101.12737/) (2021)
- [How should AI decisions be explained? Requirements for Explanations from the Perspective of European Law](https://mlsanity.com/paper/2404.12762/) (2024)

## Built on by (most cited first, 4 of 4)

- [Explanation Multiplicity in SHAP: Characterization and Assessment](https://mlsanity.com/paper/2601.12654/) (2026)
- [ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations](https://mlsanity.com/paper/2601.23068/) (2026)
- [Tractable Shapley Values and Interactions via Tensor Networks](https://mlsanity.com/paper/2510.22138/) (2025)
- [We Need Explanation Cards to Connect Explanation Algorithms to the Real World](https://mlsanity.com/paper/2606.16786/) (2026)

## Abstract (arXiv)

Local feature-based explanations are a key component of the XAI toolkit. These explanations compute feature importance values relative to an ``interpretable'' feature representation. In tabular data, feature values themselves are often considered interpretable. This paper examines the impact of data engineering choices on local feature-based explanations. We demonstrate that simple, common data engineering techniques, such as representing age with a histogram or encoding race in a specific way, can manipulate feature importance as determined by popular methods like SHAP. Notably, the sensitivity of explanations to feature representation can be exploited by adversaries to obscure issues like discrimination. While the intuition behind these results is straightforward, their systematic exploration has been lacking. Previous work has focused on adversarial attacks on feature-based explainers by biasing data or manipulating models. To the best of our knowledge, this is the first study demonstrating that explainers can be misled by standard, seemingly innocuous data engineering techniques.