mlsanityData to 14 Oct 2026

Evaluating Robustness of Counterfactual Explanations

arXiv 2103.02354 ↗First posted 3 Mar 2021cs.LG cs.AIcited by 41

Not on the map. Why?

Abstract (arXiv)

Transparency is a fundamental requirement for decision making systems when these should be deployed in the real world. It is usually achieved by providing explanations of the system's behavior. A prominent and intuitive type of explanations are counterfactual explanations. Counterfactual explanations explain a behavior to the user by proposing actions -- as changes to the input -- that would cause a different (specified) behavior of the system. However, such explanation methods can be unstable with respect to small changes to the input -- i.e. even a small change in the input can lead to huge or arbitrary changes in the output and of the explanation. This could be problematic for counterfactual explanations, as two similar individuals might get very different explanations. Even worse, if the recommended actions differ considerably in their complexity, one would consider such unstable (counterfactual) explanations as individually unfair. In this work, we formally and empirically study the robustness of counterfactual explanations in general, as well as under different models and different kinds of perturbations. Furthermore, we propose that plausible counterfactual explanations can be used instead of closest counterfactual explanations to improve the robustness and consequently the individual fairness of counterfactual explanations.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 27 of its 41 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

27 of 41 references.

References · 27

  1. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  3. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  4. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  5. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  6. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  7. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  8. 2019A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAIcited by 404
  9. 2020Fairness in Machine Learning: A Surveycited by 370
  10. 2018On the Robustness of Interpretability Methodscited by 314
  11. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  12. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
15 more
  1. 2016Model-Agnostic Interpretability of Machine Learningcited by 219
  2. 2017Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Modelscited by 206
  3. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 166
  4. 2019On the Apparent Conflict Between Individual and Group Fairnesscited by 126
  5. 2019Fooling Neural Network Interpretations via Adversarial Model Manipulationcited by 112
  6. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 72
  7. 2020On the Fairness of Causal Algorithmic Recoursecited by 70
  8. 2020Fairness Through Robustness: Investigating Robustness Disparity in Deep Learningcited by 56
  9. 2019Equalizing Recourse across Groupscited by 55
  10. 2018A Simple and Effective Model-Based Variable Importance Measurecited by 51
  11. 2020On Adversarial Bias and the Robustness of Fair Machine Learningcited by 36
  12. 2018Defining Locality for Surrogates in Post-hoc Interpretablitycited by 33
  13. 2019On the computation of counterfactual explanations -- A surveycited by 33
  14. 2020Convex Density Constraints for Computing Plausible Counterfactual Explanationscited by 32
  15. 2019Issues with post-hoc counterfactual explanations: a discussioncited by 30

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 10; 2023: 9; 2024: 13; 2025: 3; 2026: 5.

41 papers.

Sort:

By area:

  1. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  2. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 53
  3. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  4. 2022On the Robustness of Sparse Counterfactual Explanations to Adverse Perturbationscited by 32
  5. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  6. 2022The privacy issue of counterfactual explanations: explanation linkage attackscited by 20
  7. 2023Finding Regions of Counterfactual Explanations via Robust Optimizationcited by 19
  8. 2023Generating robust counterfactual explanationscited by 13
  9. 2023Robustness Implies Fairness in Causal Algorithmic Recoursecited by 12
  10. 2022Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Settingcited by 11
  11. 2024Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Changecited by 10
  12. 2022Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learningcited by 9
29 more
  1. 2022"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanationscited by 9
  2. 2023The Risks of Recourse in Binary Classificationcited by 8
  3. 2024Time Can Invalidate Algorithmic Recoursecited by 8
  4. 2023Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbationscited by 6
  5. 2024Generating Likely Counterfactuals Using Sum-Product Networkscited by 6
  6. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  7. 2023Faithful Model Explanations through Energy-Constrained Conformal Counterfactualscited by 5
  8. 2024A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanationscited by 5
  9. 2023For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAIcited by 4
  10. 2024The Effect of Data Poisoning on Counterfactual Explanationscited by 3
  11. 2024CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)cited by 3
  12. 2024A comprehensive interpretable machine learning framework for Mild Cognitive Impairment and Alzheimer's disease diagnosiscited by 3
  13. 2024Generally-Occurring Model Change for Robust Counterfactual Explanationscited by 2
  14. 2025Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventionscited by 2
  15. 2026Fair Recourse for All: Ensuring Individual and Group Fairness in Counterfactual Explanationscited by 2
  16. 2023"How to make them stay?" -- Diverse Counterfactual Explanations of Employee Attritioncited by 1
  17. 2023T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systemscited by 1
  18. 2024Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamicscited by 1
  19. 2024Explainable bank failure prediction models: Counterfactual explanations to reduce the failure riskcited by 1
  20. 2024Case-based Explainability for Random Forest: Prototypes, Critics, Counter-factuals and Semi-factualscited by 1
  21. 2024S-CFE: Simple Counterfactual Explanationscited by 1
  22. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  23. 2025Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoderscited by 1
  24. 2022Causality-Aware Local Interpretable Model-Agnostic Explanationscited by 0
  25. 2024Towards Understanding the Influence of Training Samples on Explanationscited by 0
  26. 2026On the Hardness of Computing Counterfactual and Semifactual Explanations in XAIcited by 0
  27. 2026The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanationscited by 0
  28. 2026We Need Explanation Cards to Connect Explanation Algorithms to the Real Worldcited by 0
  29. 2026Target-confidence Recourse Using tSeTlin machines: TRUSTcited by 0