Deep-Lock：深度神经网络的安全授权
Deep-Lock: Secure Authorization for Deep Neural Networks
AI总结：
本文提出了一种通用且轻量级的基于密钥的模型锁定方案Deep-Lock，通过S-Box和密钥调度算法加密DNN模型参数，确保仅在使用正确密钥时模型正常运行，且对微调攻击具有鲁棒性，适用于现有软硬件实现。
摘要：
训练好的深度神经网络（DNN）模型在多种商业模式中被视为有价值的知识产权（IP）。防止此类DNN模型的IP被盗和未经授权的使用已成为业界高度关注的问题。在本文中，我们通过提出一种通用且轻量级的基于密钥的模型锁定方案来解决防止DNN模型被未经授权使用的问题，该方案确保被锁定的模型仅在应用正确的密钥时才能正常运行。所提出的方案名为Deep-Lock，它利用具有良好安全特性的S-Box，通过密钥调度算法从主密钥生成密钥，对训练好的DNN模型的每个参数进行加密。由此得到的密集加密权重网络被证明对模型微调攻击具有鲁棒性。最后，Deep-Lock不需要对DNN模型的结构和训练进行任何干预，使其适用于所有现有的DNN软件和硬件实现。
英文摘要：
Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models. Prevention of IP theft and unauthorized usage of such DNN models has been raised as of significant concern by industry. In this paper, we address the problem of preventing unauthorized usage of DNN models by proposing a generic and lightweight key-based model-locking scheme, which ensures that a locked model functions correctly only upon applying the correct secret key. The proposed scheme, known as Deep-Lock, utilizes S-Boxes with good security properties to encrypt each parameter of a trained DNN model with secret keys generated from a master key via a key scheduling algorithm. The resulting dense network of encrypted weights is found robust against model fine-tuning attacks. Finally, Deep-Lock does not require any intervention in the structure and training of the DNN models, making it applicable for all existing software and hardware implementations of DNN.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
