Learning-Based Attacks in Cyber-Physical Systems
Learning-Based Attacks in Cyber-Physical Systems
复制标题
DOI：
10.1109/tcns.2020.3028035
复制
发表时间：
2018-09
影响因子：
4.2
通讯作者：
M. J. Khojasteh;Anatoly Khina;M. Franceschetti;T. Javidi
中科院分区：
文献类型：
--
作者：
M. J. Khojasteh;Anatoly Khina;M. Franceschetti;T. Javidi
我们在网络物理系统的简单抽象中引入了基于学习的攻击问题——离散时间、线性、时不变工厂的情况，可能会受到覆盖传感器读数和控制器操作的攻击。攻击者试图了解植物的动态，并随后覆盖控制器的驱动信号以在不被发现的情况下摧毁植物。攻击者可以使用其对工厂动态的估计向控制器提供虚构的传感器读数，并模仿合法的工厂操作。相比之下，控制者则不断地警惕攻击。一旦控制器检测到攻击，就会立即关闭工厂。在标量植物的情况下，当攻击者使用任意学习算法来估计系统动态时，我们针对任何可测量的控制策略得出攻击者欺骗概率的上限。然后，我们通过假设检查系统扰动的经验方差的认证测试来推导标量和向量工厂的攻击者欺骗概率的下限。我们还展示了控制器如何通过在“名义控制策略”之上叠加精心设计的隐私增强信号来提高系统的安全性。最后，对于属于再生核希尔伯特空间的非线性标量动力学，我们研究了基于非线性高斯过程学习算法的攻击性能。
We introduce the problem of learning-based attacks in a simple abstraction of cyber-physical systems— the case of a discrete-time, linear, time-invariant plant that may be subject to an attack that overrides sensor readings and controller actions. The attacker attempts to learn the dynamics of the plant and subsequently overrides the controller's actuation signal to destroy the plant without being detected. The attacker can feed fictitious sensor readings to the controller using its estimate of the plant dynamics and mimic the legitimate plant operation. The controller, in contrast, is constantly on the lookout for an attack; once the controller detects an attack, it immediately shuts the plant off. In the case of scalar plants, we derive an upper bound on the attacker's deception probability for any measurable control policy when the attacker uses an arbitrary learning algorithm to estimate the system dynamics. We then derive lower bounds for the attacker's deception probability for both scalar and vector plants by assuming an authentication test that inspects the empirical variance of the system disturbance. We also show how the controller can improve the security of the system by superimposing a carefully crafted privacy-enhancing signal on top of the “nominal control policy.” Finally, for nonlinear scalar dynamics that belong to the reproducing kernel Hilbert space, we investigate the performance of attacks based on nonlinear Gaussian process learning algorithms.