# SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning

arXiv: https://arxiv.org/abs/2311.13174 · HTML: https://mlsanity.com/paper/2311.13174/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 22 Nov 2023.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 14 of 14)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [SecureBoost: A Lossless Federated Learning Framework](https://mlsanity.com/paper/1901.08755/) (2019)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [On Wasserstein Two Sample Testing and Related Families of Nonparametric Tests](https://mlsanity.com/paper/1509.02237/) (2015)
- [Mixed-Privacy Forgetting in Deep Networks](https://mlsanity.com/paper/2012.13431/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [VeriFi: Towards Verifiable Federated Unlearning](https://mlsanity.com/paper/2205.12709/) (2022)
- [A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning](https://mlsanity.com/paper/2106.06312/) (2021)

## Built on by (most cited first, 4 of 4)

- [Towards Privacy-Guaranteed Label Unlearning in Vertical Federated Learning: Few-Shot Forgetting without Disclosure](https://mlsanity.com/paper/2410.10922/) (2024)
- [Online Gradient Boosting Decision Tree: In-Place Updates for Efficient Adding/Deleting Data](https://mlsanity.com/paper/2502.01634/) (2025)
- [REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature](https://mlsanity.com/paper/2512.10348/) (2025)
- [A Survey on Federated Unlearning: Challenges and Opportunities](https://mlsanity.com/paper/2403.02437/) (2024)

## Abstract (arXiv)

In response to legislation mandating companies to honor the textitright to be forgotten by erasing user data, it has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private features for model training. In VFL, data removal, i.e., textitmachine unlearning, often requires removing specific features across all samples under privacy guarentee in federated learning. To address this challenge, we propose methname, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both textitinstance unlearning and textitfeature unlearning without the need for retraining from scratch. Leveraging a robust GBDT structure, we enable effective data deletion while reducing degradation of model performance. Extensive experimental results on popular datasets demonstrate that our method achieves superior model utility and forgetfulness compared to textitstate-of-the-art methods. To our best knowledge, this is the first work that investigates machine unlearning in VFL scenarios.