# Data-Aware and Scalable Sensitivity Analysis for Decision Tree Ensembles

arXiv: https://arxiv.org/abs/2602.07453 · HTML: https://mlsanity.com/paper/2602.07453/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 7 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Fairness Testing: Testing Software for Discrimination](https://mlsanity.com/paper/1709.03221/) (2017)
- [Evasion and Hardening of Tree Ensemble Classifiers](https://mlsanity.com/paper/1509.07892/) (2015)
- [Robust Decision Trees Against Adversarial Examples](https://mlsanity.com/paper/1902.10660/) (2019)
- [Robustness Verification of Tree-based Models](https://mlsanity.com/paper/1906.03849/) (2019)
- [Versatile Verification of Tree Ensembles](https://mlsanity.com/paper/2010.13880/) (2020)
- [(De-)Randomized Smoothing for Decision Stump Ensembles](https://mlsanity.com/paper/2205.13909/) (2022)
- [Explainable Global Fairness Verification of Tree-Based Classifiers](https://mlsanity.com/paper/2209.13179/) (2022)

## Built on by (most cited first, 2 of 2)

- [Formal verification of tree-based machine learning models for lateral spreading](https://mlsanity.com/paper/2603.16983/) (2026)
- [Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach](https://mlsanity.com/paper/2605.13830/) (2026)

## Abstract (arXiv)

Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sensitive to a specified subset of features -- such as protected attributes -- whose manipulation can alter model predictions. Existing approaches often yield examples of sensitivity that lie far from the training distribution, limiting their interpretability and practical value. We propose a data-aware sensitivity framework that constrains the sensitive examples to remain close to the dataset, thereby producing realistic and interpretable evidence of model weaknesses. To this end, we develop novel techniques for data-aware search using a combination of mixed-integer linear programming (MILP) and satisfiability modulo theories (SMT) encodings. Our contributions are fourfold. First, we strengthen the NP-hardness result for sensitivity verification, showing it holds even for trees of depth 1. Second, we develop MILP-optimizations that significantly speed up sensitivity verification for single ensembles and for the first time can also handle multiclass tree ensembles. Third, we introduce a data-aware framework generating realistic examples close to the training distribution. Finally, we conduct an extensive experimental evaluation on large tree ensembles, demonstrating scalability to ensembles with up to 800 trees of depth 8, achieving substantial improvements over the state of the art. This framework provides a practical foundation for analyzing the reliability and fairness of tree-based models in high-stakes applications.