mlsanityData to 7 Oct 2026

On the Adversarial Robustness of Causal Algorithmic Recourse

arXiv 2112.11313 ↗First posted 21 Dec 2021cs.LGcited by 56

Not on the map. Why?

Abstract (arXiv)

Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods that offer minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse for linear and for differentiable classifiers. Finally, we show that regularizing the decision-making classifier to behave locally linearly and to rely more strongly on actionable features facilitates the existence of adversarially robust recourse.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

32 of 62 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2021Convex optimizationcited by 2,479
  7. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  10. 2013Domain Generalization via Invariant Feature Representationcited by 622
  11. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 420
  12. 2018Actionable Recourse in Linear Classificationcited by 327
20 more
  1. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  2. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  3. 2019Adversarial Robustness through Local Linearizationcited by 146
  4. 2017Fair Inference On Outcomescited by 143
  5. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  6. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128
  7. 2018Invariance, Causality and Robustnesscited by 123
  8. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  9. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  10. 2021Towards Robust and Reliable Algorithmic Recoursecited by 101
  11. 2016Robustness of classifiers: from adversarial to random noisecited by 87
  12. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  13. 2020On Counterfactual Explanations under Predictive Multiplicitycited by 73
  14. 2020On the Fairness of Causal Algorithmic Recoursecited by 69
  15. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  16. 2019Equalizing Recourse across Groupscited by 51
  17. 2021Evaluating Robustness of Counterfactual Explanationscited by 41
  18. 2021Consistent Counterfactuals for Deep Modelscited by 37
  19. 2020Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shiftscited by 34
  20. 2020Learning Models for Actionable Recoursecited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 9; 2023: 20; 2024: 11; 2025: 9; 2026: 7.

56 papers.

Sort:

By area:

  1. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  2. 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guaranteescited by 45
  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 Privacy Risks of Algorithmic Recoursecited by 32
  6. 2024Robust Counterfactual Explanations in Machine Learning: A Surveycited by 29
  7. 2023GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanationscited by 27
  8. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  9. 2022Improvement-Focused Causal Recourse (ICR)cited by 20
  10. 2023Provably Robust and Plausible Counterfactual Explanations for Neural Networks via Robust Optimisationcited by 20
  11. 2023Finding Regions of Counterfactual Explanations via Robust Optimizationcited by 19
  12. 2023A Review of the Role of Causality in Developing Trustworthy AI Systemscited by 14
38 more
  1. 2023Generating robust counterfactual explanationscited by 13
  2. 2023Robustness Implies Fairness in Causal Algorithmic Recoursecited by 12
  3. 2022RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Modelcited by 11
  4. 2023The Risks of Recourse in Binary Classificationcited by 8
  5. 2023The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomescited by 8
  6. 2024Time Can Invalidate Algorithmic Recoursecited by 8
  7. 2024Feature Responsiveness Scores: Model-Agnostic Explanations for Recoursecited by 8
  8. 2024Interval Abstractions for Robust Counterfactual Explanationscited by 7
  9. 2024Learning Decision Trees and Forests with Algorithmic Recoursecited by 7
  10. 2022FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanationscited by 6
  11. 2023Bayesian Hierarchical Models for Counterfactual Estimationcited by 6
  12. 2024Rigorous Probabilistic Guarantees for Robust Counterfactual Explanationscited by 6
  13. 2024A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanationscited by 5
  14. 2025From Search To Sampling: Generative Models For Robust Algorithmic Recoursecited by 5
  15. 2023Causal Adversarial Perturbations for Individual Fairness and Robustness in Heterogeneous Data Spacescited by 4
  16. 2023Prediction without Preclusion: Recourse Verification with Reachable Setscited by 4
  17. 2024Learning-Augmented Robust Algorithmic Recoursecited by 4
  18. 2025Counterfactual Explanations for Model Ensembles Using Entropic Risk Measurescited by 4
  19. 2023On Minimizing the Impact of Dataset Shifts on Actionable Explanationscited by 3
  20. 2023Causal Fair Metric: Bridging Causality, Individual Fairness, and Adversarial Robustnesscited by 3
  21. 2025Optimal Robust Recourse with Lp-Bounded Model Changecited by 3
  22. 2025Reinforcement Learning for Durable Algorithmic Recoursecited by 3
  23. 2023Algorithmic Recourse with Missing Valuescited by 2
  24. 2023Explaining and visualizing black-box models through counterfactual pathscited by 2
  25. 2024Towards Non-Adversarial Algorithmic Recoursecited by 2
  26. 2024Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recoursecited by 2
  27. 2024HR-Bandit: Human-AI Collaborated Linear Recourse Banditcited by 2
  28. 2025Counterfactual Explanations for Time Series Should be Human-Centered and Temporally Coherent in Interventionscited by 2
  29. 2022Provable Robust Saliency-based Explanationscited by 1
  30. 2023Iterative Partial Fulfillment of Counterfactual Explanations: Benefits and Riskscited by 1
  31. 2025Understanding Fixed Predictions via Confined Regionscited by 1
  32. 2025Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoderscited by 1
  33. 2026From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recoursecited by 1
  34. 2023Estimation of Counterfactual Interventions under Uncertaintiescited by 0
  35. 2023On the Trade-offs between Adversarial Robustness and Actionable Explanationscited by 0
  36. 2023Algorithmic Recourse in Abnormal Multivariate Time Seriescited by 0
  37. 2025A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretabilitycited by 0
  38. 2025Wasserstein Distributionally Robust Optimization Through the Lens of Structural Causal Models and Individual Fairnesscited by 0

50 most cited of 56 All 56 (JSON)