mlsanityData to 14 Oct 2026

Trust Regions for Explanations via Black-Box Probabilistic Certification

arXiv 2402.11168 ↗First posted 17 Feb 2024cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i.e., ℓ∞ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a trust region has multiple benefits: i) insight into model behavior in a region, with a guarantee; ii) ascertained stability of the explanation; iii) explanation reuse, which can save time, energy and money by not having to find explanations for every example; and iv) a possible meta-metric to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 39 of its 61 references that are in the map. First posted on arXiv 17 Feb 2024.

Builds on

39 of 61 references.

References · 39

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  7. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  8. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 838
  9. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  10. 2018A Tutorial on Bayesian Optimizationcited by 744
  11. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  12. 2014OpenML: networked science in machine learningcited by 526
27 more
  1. 2019Introduction to Multi-Armed Banditscited by 481
  2. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 345
  3. 2018Actionable Recourse in Linear Classificationcited by 328
  4. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 262
  5. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  6. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
  7. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 179
  8. 2019Complexity of Linear Regions in Deep Networkscited by 167
  9. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  10. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  11. 2020Hyper-Parameter Optimization: A Review of Algorithms and Applicationscited by 114
  12. 2020SoK: Certified Robustness for Deep Neural Networkscited by 105
  13. 2018Boolean Decision Rules via Column Generationcited by 80
  14. 2014Falling Rule Listscited by 59
  15. 2023Robust Counterfactual Explanations for Neural Networks With Probabilistic Guaranteescited by 45
  16. 2019Model Agnostic Contrastive Explanations for Structured Datacited by 41
  17. 2022Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recoursecited by 40
  18. 2022Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AIcited by 40
  19. 2021Consistent Counterfactuals for Deep Modelscited by 37
  20. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  21. 2019Robustness Verification of Tree-based Modelscited by 33
  22. 2021To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methodscited by 26
  23. 2020Model Agnostic Multilevel Explanationscited by 24
  24. 2019On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Methodcited by 21
  25. 2023Finding Regions of Counterfactual Explanations via Robust Optimizationcited by 19
  26. 2017ZOOpt: Toolbox for Derivative-Free Optimizationcited by 12
  27. 2022Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2025Counterfactual Explanations for Model Ensembles Using Entropic Risk Measurescited by 5
  2. 2025Pixel-level Certified Explanations via Randomized Smoothingcited by 4
  3. 2024CELL your Model: Contrastive Explanations for Large Language Modelscited by 0
  4. 2026We Need Explanation Cards to Connect Explanation Algorithms to the Real Worldcited by 0