Secure learning-based MPC via garbled circuit
Secure learning-based MPC via garbled circuit
复制标题
通过乱码电路实现基于学习的安全 MPC
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. S. Darup
中科院分区：
文献类型：
--
作者：
K. Tjell;Natalie Schluter;P. Binfet;M. S. Darup
加密控制在基于云或联网的系统中寻求机密的控制器评估。许多现有方法都建立在同态加密（HE）的基础上，允许对加密数据进行简单的数学运算。不幸的是，他是计算要求很高，许多控制法（特别是非多项式的）不能有效地实现与此technology.We在本文中表明，安全的两方计算使用乱码电路提供了一个强大的替代他加密控制。更确切地说，我们提出了一种新的方案，允许有效地实现（非多项式）最大输出神经网络与一个隐藏层在一个安全的方式。这些网络对控制特别感兴趣，因为它们原则上允许精确地描述分段仿射控制律，例如，线性模型预测控制（MPC）。然而，精确拟合需要神经元的高维预激活。幸运的是，我们说明了即使是低维的基于学习的近似是足够准确的线性MPC。此外，这些近似可以安全地评估使用乱码电路在不到100毫秒的数值例子。因此，我们的方法为应用加密控制提供了新的机会。
Encrypted control seeks confidential controller evaluation in cloud-based or networked systems. Many existing approaches build on homomorphic encryption (HE) that allow simple mathematical operations to be carried out on encrypted data. Unfortunately, HE is computationally demanding and many control laws (in particular non-polynomial ones) cannot be efficiently implemented with this technology.We show in this paper that secure two-party computation using garbled circuits provides a powerful alternative to HE for encrypted control. More precisely, we present a novel scheme that allows to efficiently implement (non-polynomial) max-out neural networks with one hidden layer in a secure fashion. These networks are of special interest for control since they allow, in principle, to exactly describe piecewise affine control laws resulting from, e.g., linear model predictive control (MPC). However, exact fits require high-dimensional preac-tivations of the neurons. Fortunately, we illustrate that even low-dimensional learning-based approximations are sufficiently accurate for linear MPC. In addition, these approximations can be securely evaluated using garbled circuit in less than 100 ms for our numerical example. Hence, our approach opens new opportunities for applying encrypted control.