论文标题
通过标签分布扰动的深度神经网络的定制水印
Customized Watermarking for Deep Neural Networks via Label Distribution Perturbation
论文作者
论文摘要
随着机器学习的应用价值的不断增长，深神经网络（DNN）的知识产权（IP）权利正在越来越关注。通过我们的分析，大多数现有的DNN水印方法都可以抵抗微调和修剪攻击，但蒸馏攻击。为了解决这些问题，我们提出了一个新的DNN水印框架，统一的软标签扰动（USP），其探测器与要水印的模型配对，并定制软标签扰动（CSP），通过将扰动添加到模型输出概率分布中，将水印嵌入水印。实验结果表明，我们的方法可以抵抗所有水印去除攻击，并且在蒸馏攻击中表现跑赢大盘。此外，我们在主要任务和水印之间也取决于98.68％的水印精度，而仅影响主要任务准确性的0.59％。
With the increasing application value of machine learning, the intellectual property (IP) rights of deep neural networks (DNN) are getting more and more attention. With our analysis, most of the existing DNN watermarking methods can resist fine-tuning and pruning attack, but distillation attack. To address these problem, we propose a new DNN watermarking framework, Unified Soft-label Perturbation (USP), having a detector paired with the model to be watermarked, and Customized Soft-label Perturbation (CSP), embedding watermark via adding perturbation into the model output probability distribution. Experimental results show that our methods can resist all watermark removal attacks and outperform in distillation attack. Besides, we also have an excellent trade-off between the main task and watermarking that achieving 98.68% watermark accuracy while only affecting the main task accuracy by 0.59%.
