# Robust and Stable Black Box Explanations

arXiv: https://arxiv.org/abs/2011.06169 · HTML: https://mlsanity.com/paper/2011.06169/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2020.

## Built on by (most cited first, 30 of 47)

- [From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI](https://mlsanity.com/paper/2201.08164/) (2022)
- [Towards Robust and Reliable Algorithmic Recourse](https://mlsanity.com/paper/2102.13620/) (2021)
- [Framework for Evaluating Faithfulness of Local Explanations](https://mlsanity.com/paper/2202.00734/) (2022)
- [Do Input Gradients Highlight Discriminative Features?](https://mlsanity.com/paper/2102.12781/) (2021)
- [Post Hoc Explanations of Language Models Can Improve Language Models](https://mlsanity.com/paper/2305.11426/) (2023)
- [Adversarial attacks and defenses in explainable artificial intelligence: A survey](https://mlsanity.com/paper/2306.06123/) (2023)
- [A Framework for Learning Ante-hoc Explainable Models via Concepts](https://mlsanity.com/paper/2108.11761/) (2021)
- [A Survey on the Robustness of Feature Importance and Counterfactual Explanations](https://mlsanity.com/paper/2111.00358/) (2021)
- [Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods](https://mlsanity.com/paper/2106.09078/) (2021)
- [Provably efficient, succinct, and precise explanations](https://mlsanity.com/paper/2111.01576/) (2021)
- [Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing](https://mlsanity.com/paper/2108.04990/) (2021)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [Robust Explanation Constraints for Neural Networks](https://mlsanity.com/paper/2212.08507/) (2022)
- [Understanding and Enhancing Robustness of Concept-based Models](https://mlsanity.com/paper/2211.16080/) (2022)
- [On the Lack of Robust Interpretability of Neural Text Classifiers](https://mlsanity.com/paper/2106.04631/) (2021)
- [Connecting Interpretability and Robustness in Decision Trees through Separation](https://mlsanity.com/paper/2102.07048/) (2021)
- [Inferring Sensitive Attributes from Model Explanations](https://mlsanity.com/paper/2208.09967/) (2022)
- [Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools](https://mlsanity.com/paper/2110.07120/) (2021)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Rethinking Explainable Machine Learning as Applied Statistics](https://mlsanity.com/paper/2402.02870/) (2024)
- [A Query-Optimal Algorithm for Finding Counterfactuals](https://mlsanity.com/paper/2207.07072/) (2022)
- [Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions](https://mlsanity.com/paper/2206.12481/) (2022)
- [Confident Feature Ranking](https://mlsanity.com/paper/2307.15361/) (2023)
- [Self-learn to Explain Siamese Networks Robustly](https://mlsanity.com/paper/2109.07371/) (2021)
- [X Hacking: The Threat of Misguided AutoML](https://mlsanity.com/paper/2401.08513/) (2024)
- [When Can You Trust Your Explanations? A Robustness Analysis on Feature Importances](https://mlsanity.com/paper/2406.14349/) (2024)
- [An empirical study of the effect of background data size on the stability of SHapley Additive exPlanations (SHAP) for deep learning models](https://mlsanity.com/paper/2204.11351/) (2022)
- [Extending LIME for Business Process Automation](https://mlsanity.com/paper/2108.04371/) (2021)
- [Explaining the root causes of unit-level changes](https://mlsanity.com/paper/2206.12986/) (2022)
- [Rethinking Robustness of Model Attributions](https://mlsanity.com/paper/2312.10534/) (2023)

## Abstract (arXiv)

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However, existing algorithms for generating such explanations have been shown to lack stability and robustness to distribution shifts. We propose a novel framework for generating robust and stable explanations of black box models based on adversarial training. Our framework optimizes a minimax objective that aims to construct the highest fidelity explanation with respect to the worst-case over a set of adversarial perturbations. We instantiate this algorithm for explanations in the form of linear models and decision sets by devising the required optimization procedures. To the best of our knowledge, this work makes the first attempt at generating post hoc explanations that are robust to a general class of adversarial perturbations that are of practical interest. Experimental evaluation with real-world and synthetic datasets demonstrates that our approach substantially improves robustness of explanations without sacrificing their fidelity on the original data distribution.