The surge in popularity of machine learning (ML) has driven significant investments in training Deep Neural Networks (DNNs). However, these models that require resource-intensive training are vulnerable to theft and unauthorized use. This paper addresses this challenge by introducing DNNShield, a novel approach for DNN protection that integrates seamlessly before training. DNNShield embeds unique identifiers within the model architecture using specialized protection layers. These layers enable secure training and deployment while offering high resilience against various attacks, including fine-tuning, pruning, and adaptive adversarial attacks. Notably, our approach achieves this security with minimal performance and computational overhead (less than 5\% runtime increase). We validate the effectiveness and efficiency of DNNShield through extensive evaluations across three datasets and four model architectures. This practical solution empowers developers to protect their DNNs and intellectual property rights.

翻译：机器学习（ML）的迅猛发展推动了对深度神经网络（DNN）训练的大量投资。然而，这些需要大量资源训练的模型极易遭受窃取和未授权使用。本文通过提出DNNShield（一种在训练前无缝集成的DNN保护新方法）来应对这一挑战。DNNShield利用专用保护层在模型架构中嵌入唯一标识符。这些层在实现安全训练与部署的同时，对微调、剪枝和自适应对抗攻击等多种攻击方式具有高鲁棒性。值得注意的是，我们的方法仅通过极小的性能与计算开销（运行时增加低于5%）即可实现此安全防护。我们通过在三类数据集和四种模型架构上的广泛评估，验证了DNNShield的有效性与高效性。这一实用解决方案使开发者能够保护其DNN模型及知识产权权益。