Robust Watermarking on Gradient Boosting Decision Trees
This addresses the need for protecting GBDT models in industry and academia, which is an incremental advancement as watermarking for GBDTs was previously underexplored compared to neural networks.
The paper tackles the problem of watermarking Gradient Boosting Decision Trees (GBDTs) by introducing a robust framework that embeds imperceptible watermarks, achieving high embedding rates and low accuracy degradation across diverse datasets.
Gradient Boosting Decision Trees (GBDTs) are widely used in industry and academia for their high accuracy and efficiency, particularly on structured data. However, watermarking GBDT models remains underexplored 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.