# Verifying Robustness of Gradient Boosted Models

arXiv: https://arxiv.org/abs/1906.10991 · HTML: https://mlsanity.com/paper/1906.10991/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2019.

## Built on by (most cited first, 13 of 13)

- [On Explaining Random Forests with SAT](https://mlsanity.com/paper/2105.10278/) (2021)
- [A Review of Formal Methods applied to Machine Learning](https://mlsanity.com/paper/2104.02466/) (2021)
- [SaDe: Learning Models that Provably Satisfy Domain Constraints](https://mlsanity.com/paper/2112.00552/) (2021)
- [Verifiable Learning for Robust Tree Ensembles](https://mlsanity.com/paper/2305.03626/) (2023)
- [Scaling up Memory-Efficient Formal Verification Tools for Tree Ensembles](https://mlsanity.com/paper/2105.02595/) (2021)
- [Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs](https://mlsanity.com/paper/2207.02295/) (2022)
- [ITBoost: Information-Theoretic Trust for Robust Boosting](https://mlsanity.com/paper/2605.04671/) (2026)
- [Faster Repeated Evasion Attacks in Tree Ensembles](https://mlsanity.com/paper/2402.08586/) (2024)
- [A Geometric Method for Improved Uncertainty Estimation in Real-time](https://mlsanity.com/paper/2206.11562/) (2022)
- [Adversarial Example Detection in Deployed Tree Ensembles](https://mlsanity.com/paper/2206.13083/) (2022)
- [Uncertainty Estimation based on Geometric Separation](https://mlsanity.com/paper/2301.04452/) (2023)
- [Probabilistic ML Verification via Weighted Model Integration](https://mlsanity.com/paper/2402.04892/) (2024)
- [Verifiable Boosted Tree Ensembles](https://mlsanity.com/paper/2402.14988/) (2024)

## Abstract (arXiv)

Gradient boosted models are a fundamental machine learning technique. Robustness to small perturbations of the input is an important quality measure for machine learning models, but the literature lacks a method to prove the robustness of gradient boosted models. This work introduces VeriGB, a tool for quantifying the robustness of gradient boosted models. VeriGB encodes the model and the robustness property as an SMT formula, which enables state of the art verification tools to prove the model's robustness. We extensively evaluate VeriGB on publicly available datasets and demonstrate a capability for verifying large models. Finally, we show that some model configurations tend to be inherently more robust than others.