通过神经元授权的边缘深度学习模型保护
Edge Deep Learning Model Protection via Neuron Authorization
摘要：
随着深度学习处理器和加速器的发展，深度学习模型已经作为物联网的一部分广泛部署在边缘设备上。边缘设备模型通常被认为是有价值的知识产权，值得仔细保护。不幸的是，这些模型有很大的被盗或非法复制的风险。现有的基于加密算法的模型保护存在计算开销大的问题，由于边缘设备的计算能力有限，计算开销大是不现实的。在这项工作中，我们提出了一个轻量级的，实用的，通用的边缘设备模型保护方法在神经元级别，表示为EdgePro。具体来说，我们选择几个神经元作为授权神经元，并将其激活值设置为锁定值，并在训练期间将神经元输出缩放为“asswords”。EdgePro通过确保模型只有在满足“密码”时才能正确工作来保护模型，其代价是加密和存储“密码”的信息，而不是整个模型。大量的实验结果表明，EdgePro可以很好地完成不同模式数据集的保护任务。EdgePro的推理时间增加仅为最先进方法的60%，准确性损失小于1%。此外，EdgePro对自适应攻击（包括微调和修剪）具有鲁棒性，这使得它在现实世界的应用中更加实用。EdgePro也是开源的，以方便未来的研究：https://github.com/Leon022/Edg
英文摘要：
With the development of deep learning processors and accelerators, deep learning models have been widely deployed on edge devices as part of the Internet of Things. Edge device models are generally considered as valuable intellectual properties that are worth for careful protection. Unfortunately, these models have a great risk of being stolen or illegally copied. The existing model protections using encryption algorithms are suffered from high computation overhead which is not practical due to the limited computing capacity on edge devices. In this work, we propose a light-weight, practical, and general Edge device model Pro tection method at neuron level, denoted as EdgePro. Specifically, we select several neurons as authorization neurons and set their activation values to locking values and scale the neuron outputs as the "asswords" during training. EdgePro protects the model by ensuring it can only work correctly when the "passwords" are met, at the cost of encrypting and storing the information of the "passwords" instead of the whole model. Extensive experimental results indicate that EdgePro can work well on the task of protecting on datasets with different modes. The inference time increase of EdgePro is only 60% of state-of-the-art methods, and the accuracy loss is less than 1%. Additionally, EdgePro is robust against adaptive attacks including fine-tuning and pruning, which makes it more practical in real-world applications. EdgePro is also open sourced to facilitate future research: https://github.com/Leon022/Edg
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。
