mlsanityData to 14 Oct 2026

The privacy issue of counterfactual explanations: explanation linkage attacks

arXiv 2210.12051 ↗First posted 21 Oct 2022cs.LG cs.CR cs.CYcited by 20

Not on the map. Why?

Abstract (arXiv)

Black-box machine learning models are being used in more and more high-stakes domains, which creates a growing need for Explainable AI (XAI). Unfortunately, the use of XAI in machine learning introduces new privacy risks, which currently remain largely unnoticed. We introduce the explanation linkage attack, which can occur when deploying instance-based strategies to find counterfactual explanations. To counter such an attack, we propose k-anonymous counterfactual explanations and introduce pureness as a new metric to evaluate the validity of these k-anonymous counterfactual explanations. Our results show that making the explanations, rather than the whole dataset, k- anonymous, is beneficial for the quality of the explanations.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 19 of its 67 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

19 of 67 references.

References · 19

  1. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  2. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 233
  3. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  4. 2020Multi-Objective Counterfactual Explanationscited by 157
  5. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  6. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  7. 2021Trustworthy AI: A Computational Perspectivecited by 93
  8. 2020On the Privacy Risks of Algorithmic Fairnesscited by 82
  9. 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
  10. 2020On Counterfactual Explanations under Predictive Multiplicitycited by 74
  11. 2020When Machine Learning Meets Privacy: A Survey and Outlookcited by 68
  12. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
7 more
  1. 2020Model extraction from counterfactual explanationscited by 47
  2. 2021Evaluating Robustness of Counterfactual Explanationscited by 41
  3. 2020Model Explanations with Differential Privacycited by 23
  4. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  5. 2021k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifierscited by 12
  6. 2022On the amplification of security and privacy risks by post-hoc explanations in machine learning modelscited by 8
  7. 2019On the Privacy Risks of Model Explanationscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 9; 2025: 5; 2026: 3.

20 papers.

Sort:

By area:

  1. 2024Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theorycited by 14
  2. 2022Privacy Meets Explainability: A Comprehensive Impact Benchmarkcited by 9
  3. 2024Counterfactual Concept Bottleneck Modelscited by 7
  4. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6
  5. 2023Privacy-Preserving Algorithmic Recoursecited by 5
  6. 2024Privacy Implications of Explainable AI in Data-Driven Systemscited by 3
  7. 2025Beware of "Explanations" of AIcited by 3
  8. 2023Unveiling the Potential of Counterfactuals Explanations in Employabilitycited by 2
  9. 2024Private Counterfactual Retrievalcited by 2
  10. 2025Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Reviewcited by 2
  11. 2026Linear Model Extraction via Factual and Counterfactual Queriescited by 2
  12. 2024Introducing User Feedback-based Counterfactual Explanations (UFCE)cited by 1
8 more
  1. 2024Contrastive Explainable Clustering with Differential Privacycited by 1
  2. 2025Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligencecited by 1
  3. 2025Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularizationcited by 1
  4. 2024Watermarking Counterfactual Explanationscited by 0
  5. 2024Private Counterfactual Retrieval With Immutable Featurescited by 0
  6. 2025What If, But Privately: Private Counterfactual Retrievalcited by 0
  7. 2026Quantifying the Privacy of Counterfactuals by Leveraging Membership Inference Attacks Against Synthetic Datacited by 0
  8. 2026SoK: Privacy Attacks on Machine Learning via Explainable AIcited by 0