# Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations

arXiv: https://arxiv.org/abs/2603.15867 · HTML: https://mlsanity.com/paper/2603.15867/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 20 of 20)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations](https://mlsanity.com/paper/1505.05116/) (2015)
- [Consistent Individualized Feature Attribution for Tree Ensembles](https://mlsanity.com/paper/1802.03888/) (2018)
- [Variance-based regularization with convex objectives](https://mlsanity.com/paper/1610.02581/) (2016)
- [Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis](https://mlsanity.com/paper/2111.04138/) (2021)
- [Mandoline: Model Evaluation under Distribution Shift](https://mlsanity.com/paper/2107.00643/) (2021)
- [A Distributionally Robust Approach to Fair Classification](https://mlsanity.com/paper/2007.09530/) (2020)
- [COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks](https://mlsanity.com/paper/2305.06754/) (2023)
- [Measuring the Robustness of NLP Models to Domain Shifts](https://mlsanity.com/paper/2306.00168/) (2023)
- [Confidence Intervals for Testing Disparate Impact in Fair Learning](https://mlsanity.com/paper/1807.06362/) (2018)
- [Fairness seen as Global Sensitivity Analysis](https://mlsanity.com/paper/2103.04613/) (2021)
- [Regularization for Wasserstein Distributionally Robust Optimization](https://mlsanity.com/paper/2205.08826/) (2022)
- [Measuring and signing fairness as performance under multiple stakeholder distributions](https://mlsanity.com/paper/2207.09960/) (2022)
- [Explaining Machine Learning Models using Entropic Variable Projection](https://mlsanity.com/paper/1810.07924/) (2018)
- [Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals](https://mlsanity.com/paper/2505.13118/) (2025)
- [Quantile-constrained Wasserstein projections for robust interpretability of numerical and machine learning models](https://mlsanity.com/paper/2209.11539/) (2022)
- [Exposing the Illusion of Fairness: Auditing Vulnerabilities to Distributional Manipulation Attacks](https://mlsanity.com/paper/2507.20708/) (2025)

## Abstract (arXiv)

The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainability framework that leverages Optimal Transport and Distributionally Robust Optimization to analyze how ML algorithms respond to constrained data perturbations. Our approach enforces constraints on feature-level statistics (e.g., brightness, age distribution), generating realistic perturbations that preserve semantic structure. We provide a model-agnostic diagnostic bench that applies to both tabular and image domains with solid theoretical guarantees. We validate the approach on real-world datasets providing interpretable robustness diagnostics that complement standard evaluation and fairness auditing tools.