Bayesian Estimation of Oscillator Parameters: Toward Anomaly Detection and Cyber-Physical System Security

Abstract

Cyber-physical system security presents unique challenges to conventional measurement science and technology. Anomaly detection in software-assisted physical systems, such as those employed in additive manufacturing or in DNA synthesis, is often hampered by the limited available parameter space of the underlying mechanism that is transducing the anomaly. As a result, the formulation of anomaly detection for such systems often leads to inverse or ill-posed problems, requiring statistical treatments. Here, we present Bayesian inference of unknown parameters associated with a generic actuator considered as a representative vital element of a cyber-physical system. Via a series of experimental input-output measurements, a transfer function for the actuator is obtained numerically, which serves as our model for the proposed method. Linear, nonlinear, and delayed dynamics may be assumed for the actuator response. By devising a code-based malicious signal, we study the efficacy of Bayesian inference for its potential to produce a detection, including uncertainty quantification, with a remarkably small number of input data points. Our approach should be adaptable to a variety of real-time cyber-physical anomaly detection scenarios.

Exploring quantum learning in the smart grid through the evolution of noisy finite fourier series

“…Data-driven machine learning techniques are under investigation and implementation as a possible first line of defense against cyberattacks given their propensity to model complex relationships (not easily described through explicit rules) to automatically discover (new) cyberattack patterns and anomalous modes of operation. Machine learning for the security of general cyber-physical systems (Lukens et al, 2022) as well the more specific security of the smart grid is an active area of research (Ashrafuzzaman et al, 2020;Karimipour et al, 2019;Khaw et al, 2020;Jahromi et al, 2020, Jahromi et al, 2021Zhang et al 2021) that has already shown promising results. The authors in Ashrafuzzaman et al (2020) develop an ensemble technique that can classify different kinds of cyberattacks; the technique works well, but there is potential for improvement in the case of very heavily imbalanced data.…”