mlsanityData to 14 Oct 2026

On the Privacy Risks of Algorithmic Recourse

arXiv 2211.05427 ↗First posted 10 Nov 2022cs.LG cs.AI cs.CRcited by 32

On the map: LLM safety and security → Membership inference attacks

Abstract (arXiv)

As predictive models are increasingly being employed to make consequential decisions, there is a growing emphasis on developing techniques that can provide algorithmic recourse to affected individuals. While such recourses can be immensely beneficial to affected individuals, potential adversaries could also exploit these recourses to compromise privacy. In this work, we make the first attempt at investigating if and how an adversary can leverage recourses to infer private information about the underlying model's training data. To this end, we propose a series of novel membership inference attacks which leverage algorithmic recourse. More specifically, we extend the prior literature on membership inference attacks to the recourse setting by leveraging the distances between data instances and their corresponding counterfactuals output by state-of-the-art recourse methods. Extensive experimentation with real world and synthetic datasets demonstrates significant privacy leakage through recourses. Our work establishes unintended privacy leakage as an important risk in the widespread adoption of recourse methods.

Key facts. Cited by 32 papers in the map (data through 14 Oct 2026). Placed in Membership inference attacks, one of 12 directions in LLM safety and security. Builds on 42 of its 52 references that are in the map. First posted on arXiv 10 Nov 2022.

Builds on

42 of 52 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Membership Inference Attacks From First Principles7 Dec
  2. 2021Enhanced Membership Inference Attacks against Machine Learning Models18 Nov

Other references · 40

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  6. 2017SmoothGrad: removing noise by adding noisecited by 1,109
  7. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  8. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  9. 2020Label-Only Membership Inference Attackscited by 388
  10. 2018Actionable Recourse in Linear Classificationcited by 328
  11. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  12. 2018Scalable Private Learning with PATEcited by 269
28 more
  1. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 262
  2. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  3. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  4. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  5. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  6. 2020Multi-Objective Counterfactual Explanationscited by 157
  7. 2019Learning Model-Agnostic Counterfactual Explanations for Tabular Datacited by 146
  8. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  9. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 144
  10. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 140
  11. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 131
  12. 2020Tempered Sigmoid Activations for Deep Learning with Differential Privacycited by 122
  13. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  14. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  15. 2021Towards Robust and Reliable Algorithmic Recoursecited by 102
  16. 2020Getting a CLUE: A Method for Explaining Uncertainty Estimatescited by 92
  17. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 86
  18. 2017Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweakingcited by 76
  19. 2020On the Fairness of Causal Algorithmic Recoursecited by 70
  20. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  21. 2019Equalizing Recourse across Groupscited by 55
  22. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  23. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 50
  24. 2020Model extraction from counterfactual explanationscited by 47
  25. 2020Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shiftscited by 36
  26. 2021Counterfactual Explanations for Arbitrary Regression Modelscited by 22
  27. 2022On the Trade-Off between Actionable Explanations and the Right to be Forgottencited by 20
  28. 2020Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recoursescited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 9; 2025: 5; 2026: 8.

32 papers.

Sort:

By area:

  1. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  2. 2023MoPe: Model Perturbation-based Privacy Attacks on Language Modelscited by 25
  3. 2023Gaussian Membership Inference Privacycited by 21
  4. 2024Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theorycited by 14
  5. 2022"Explain it in the Same Way!" -- Model-Agnostic Group Fairness of Counterfactual Explanationscited by 9
  6. 2023The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomescited by 8
  7. 2024Time Can Invalidate Algorithmic Recoursecited by 8
  8. 2023SoK: Unintended Interactions among Machine Learning Defenses and Riskscited by 6
  9. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  10. 2023Accurate, Explainable, and Private Models: Providing Recourse While Minimizing Training Data Leakagecited by 5
  11. 2023Privacy-Preserving Algorithmic Recoursecited by 5
  12. 2026Benchmarking Empirical Privacy Protection for Adaptations of Large Language Modelscited by 4
20 more
  1. 2025From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attackscited by 3
  2. 2023Algorithmic Recourse with Missing Valuescited by 2
  3. 2023Towards Regulatable AI Systems: Technical Gaps and Policy Opportunitiescited by 2
  4. 2024Private Counterfactual Retrievalcited by 2
  5. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  6. 2024Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamicscited by 1
  7. 2024Knowledge Distillation-Based Model Extraction Attack using GAN-based Private Counterfactual Explanationscited by 1
  8. 2024Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inferencecited by 1
  9. 2025Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligencecited by 1
  10. 2025Out-of-Distribution Detection using Counterfactual Distancecited by 1
  11. 2026DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakagecited by 1
  12. 2026Explanations Leak: Membership Inference with Differential Privacy and Active Learning Defensecited by 1
  13. 2026From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recoursecited by 1
  14. 2024Watermarking Counterfactual Explanationscited by 0
  15. 2024Private Counterfactual Retrieval With Immutable Featurescited by 0
  16. 2025What If, But Privately: Private Counterfactual Retrievalcited by 0
  17. 2026Explainable AI Isn't Enough! Rethinking Algorithmic Contestabilitycited by 0
  18. 2026Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Datacited by 0
  19. 2026SoK: Privacy Attacks on Machine Learning via Explainable AIcited by 0
  20. 2026Explanations-Driven Active Feature Acquisition for Algorithmic Recoursecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning
  2. 2026A Critical Review on the Effectiveness and Privacy Threats of Membership Inference Attacks
  3. 2024Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
  4. 2025Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks
  5. 2023Can Membership Inferencing be Refuted?
  6. 2022Membership Inference Attacks via Adversarial Examples
  7. 2024Better Membership Inference Privacy Measurement through Discrepancy
  8. 2023Students Parrot Their Teachers: Membership Inference on Model Distillation