为梯度提升树模型设计了首个抗干扰水印方案，嵌入隐蔽且耐用。
Robust Watermarking on Gradient Boosting Decision Trees
- 通过就地微调嵌入水印，保持模型精度
- 水印嵌入率高，准确率下降低于1%
- 对部署后微调有强鲁棒性，适合工业级应用
梯度提升决策树（GBDT）因其高精度和高效性，在工业界和学术界广泛用于结构化数据。然而，与神经网络相比，针对GBDT模型的水印技术仍研究不足。本文提出首个专为GBDT设计的鲁棒水印框架，采用就地微调方法嵌入不可感知且持久的水印。我们设计了四种嵌入策略，均在最小化模型准确率影响的同时确保水印鲁棒性。在多个数据集上的实验表明，该方法实现高水印嵌入率、低准确率损失（<1%），并对部署后的微调具有强抵抗力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。