Robust Watermarking on Gradient Boosting Decision Trees
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (25) · 20624-20633
DOI: 10.1609/aaai.v40i25.39199 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jun Woo Chung und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Gradient Boosting Decision Trees (GBDTs) are widely used in industry and academia for their high accuracy and efficiency, particularly on structured data. However, the subject of watermarking GBDT models remains underexplored, especially compared to neural networks. In this work, we present the first robust watermarking framework tailored to GBDT models, utilizing in-place fine-tuning to embed imperceptible and resilient watermarks. We propose four embedding strategies, each designed to minimize impact on model accuracy while ensuring watermark robustness. Through experiments across diverse datasets, we demonstrate that our methods achieve high watermark embedding rates, low accuracy degradation, and strong resistance to post-deployment fine-tuning.
Zitieren
APA
Chung, J. W., Lao, Y., & Zhao, W. (2026). Robust Watermarking on Gradient Boosting Decision Trees. Proceedings of the AAAI Conference on Artificial Intelligence, 40(25), 20624-20633. https://doi.org/10.1609/aaai.v40i25.39199
Vancouver
Chung JW, Lao Y, Zhao W. Robust Watermarking on Gradient Boosting Decision Trees. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(25):20624-20633. doi:10.1609/aaai.v40i25.39199
BibTeX
@article{Chung2026,
author = {Chung, Jun Woo and Lao, Yingjie and Zhao, Weijie},
title = {Robust Watermarking on Gradient Boosting Decision Trees},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {25},
pages = {20624--20633},
doi = {10.1609/aaai.v40i25.39199}
}
EUVIMED