# When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances

arXiv: https://arxiv.org/abs/2406.14349 · HTML: https://mlsanity.com/paper/2406.14349/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 20 Jun 2024.

## Builds on (most cited first, 17 of 17)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Towards Robust Interpretability with Self-Explaining Neural Networks](https://mlsanity.com/paper/1806.07538/) (2018)
- [Interpretation of Neural Networks is Fragile](https://mlsanity.com/paper/1710.10547/) (2017)
- [Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods](https://mlsanity.com/paper/1911.02508/) (2019)
- [On the Robustness of Interpretability Methods](https://mlsanity.com/paper/1806.08049/) (2018)
- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Evaluating and Aggregating Feature-based Model Explanations](https://mlsanity.com/paper/2005.00631/) (2020)
- [The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01602/) (2022)
- [Learning Model-Agnostic Counterfactual Explanations for Tabular Data](https://mlsanity.com/paper/1910.09398/) (2019)
- [Fairwashing Explanations with Off-Manifold Detergent](https://mlsanity.com/paper/2007.09969/) (2020)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [Robust and Stable Black Box Explanations](https://mlsanity.com/paper/2011.06169/) (2020)
- [A Survey on the Robustness of Feature Importance and Counterfactual Explanations](https://mlsanity.com/paper/2111.00358/) (2021)
- [A simple defense against adversarial attacks on heatmap explanations](https://mlsanity.com/paper/2007.06381/) (2020)
- [Do Not Trust Additive Explanations](https://mlsanity.com/paper/1903.11420/) (2019)

## Built on by (most cited first, 5 of 5)

- [Beyond the Single-Best Model: Rashomon Partial Dependence Profile for Trustworthy Explanations in AutoML](https://mlsanity.com/paper/2507.14744/) (2025)
- [Activation-Deactivation: A General Framework for Robust Post-hoc Explainable AI](https://mlsanity.com/paper/2510.01038/) (2025)
- [Beyond single-model XAI: aggregating multi-model explanations for enhanced trustworthiness](https://mlsanity.com/paper/2510.11164/) (2025)
- [Rashomon Sets and Model Multiplicity in Federated Learning](https://mlsanity.com/paper/2602.09520/) (2026)
- [No Single Metric Tells the Whole Story: A Multi-Dimensional Evaluation Framework for Uncertainty Attributions](https://mlsanity.com/paper/2603.24524/) (2026)

## Abstract (arXiv)

Recent legislative regulations have underlined the need for accountable and transparent artificial intelligence systems and have contributed to a growing interest in the Explainable Artificial Intelligence (XAI) field. Nonetheless, the lack of standardized criteria to validate explanation methodologies remains a major obstacle to developing trustworthy systems. We address a crucial yet often overlooked aspect of XAI, the robustness of explanations, which plays a central role in ensuring trust in both the system and the provided explanation. To this end, we propose a novel approach to analyse the robustness of neural network explanations to non-adversarial perturbations, leveraging the manifold hypothesis to produce new perturbed datapoints that resemble the observed data distribution. We additionally present an ensemble method to aggregate various explanations, showing how merging explanations can be beneficial for both understanding the model's decision and evaluating the robustness. The aim of our work is to provide practitioners with a framework for evaluating the trustworthiness of model explanations. Experimental results on feature importances derived from neural networks applied to tabular datasets highlight the importance of robust explanations in practical applications.