mlsanityData to 7 Oct 2026

XAudit : A Theoretical Look at Auditing with Explanations

arXiv 2206.04740 ↗First posted 9 Jun 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Responsible use of machine learning requires models to be audited for undesirable properties. While a body of work has proposed using explanations for auditing, how to do so and why has remained relatively ill-understood. This work formalizes the role of explanations in auditing and investigates if and how model explanations can help audits. Specifically, we propose explanation-based algorithms for auditing linear classifiers and decision trees for feature sensitivity. Our results illustrate that Counterfactual explanations are extremely helpful for auditing. While Anchors and decision paths may not be as beneficial in the worst-case, in the average-case they do aid a lot.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 14 of its 49 references that are in the map. First posted on arXiv 9 Jun 2022.

Builds on

14 of 49 references.

References · 14

  1. 2018Datasheets for Datasetscited by 1,371
  2. 2018Model Cards for Model Reportingcited by 1,068
  3. 2016End to End Learning for Self-Driving Carscited by 1,000
  4. 2020Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditingcited by 380
  5. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  6. 2020Auditing Differentially Private Machine Learning: How Private is Private SGD?cited by 213
  7. 2019Explainable Machine Learning in Deploymentcited by 210
  8. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  9. 2019Explainable AI for Trees: From Local Explanations to Global Understandingcited by 64
  10. 2022Framework for Evaluating Faithfulness of Local Explanationscited by 55
  11. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 49
  12. 2020Have you forgotten? A method to assess if machine learning models have forgotten datacited by 16
2 more
  1. 2021EMA: Auditing Data Removal from Trained Modelscited by 7
  2. 2021On the Explanatory Power of Decision Treescited by 6

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 2.

5 papers.

  1. 2024Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theorycited by 12
  2. 2024Intrinsic User-Centric Interpretability through Global Mixture of Expertscited by 9
  3. 2025Robust ML Auditing using Prior Knowledgecited by 6
  4. 2024Under manipulations, are some AI models harder to audit?cited by 5
  5. 2025ExpProof : Operationalizing Explanations for Confidential Models with ZKPscited by 1