Machine Learning IP Protection
Machine Learning IP Protection
复制标题
机器学习知识产权保护
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Ofer Rosenberg
中科院分区：
文献类型：
--
作者：
Rosario Cammarota;Indranil Banerjee;Ofer Rosenberg
机器学习，特别是深度学习正在成为应用领域的关键技术组成部分，例如身份管理，金融，汽车和医疗保健，仅举几例。专有机器学习模型 - 机器学习IP-是在网络边缘，终端设备和云中开发和部署的，以最大程度地提高用户体验。随着应用程序嵌入机器学习IP的扩散，机器学习模型和超参数对攻击者有吸引力，并且需要保护。半导体行业的主要参与者提供了设备上的机制，以保护静止和执行期间，以免被攻击者复制，更改，倒转和滥用。在这项工作中，我们探讨了系统安全体系结构机制及其在机器学习IP保护中的应用。
Machine learning, specifically deep learning is becoming a key technology component in application domains such as identity management, finance, automotive, and healthcare, to name a few. Proprietary machine learning models - Machine Learning IP - are developed and deployed at the network edge, end devices and in the cloud, to maximize user experience. With the proliferation of applications embedding Machine Learning IPs, machine learning models and hyper-parameters become attractive to attackers, and require protection. Major players in the semiconductor industry provide mechanisms on device to protect the IP at rest and during execution from being copied, altered, reverse engineered, and abused by attackers. In this work we explore system security architecture mechanisms and their applications to Machine Learning IP protection.