An Autonomous Cyber-Physical Anomaly Detection System Based on Unsupervised Disentangled Representation Learning

Cyber-Physical Systems (CPS) in heavy industry are a combination of closely integrated physical processes, networking, and scientific computing. The physical production process is monitored and controlled by the CPS in question, through advanced real-time networking systems, where high-precision feedback loops can be changed when the overgrid of cooperative computing and communication components that make up the industrial process is required. These CPS operate independently but integrate interaction capabilities as well as with the external environment, creating the connection of the physical with the digital world. The outline is that the most effective modeling and development of high-reliability CPS are directly related to the maximization of the production process, extroversion, and industrial competition. In this paper, considering the high importance of the operational status of CPS for heavy industry, an innovative autonomous anomaly detection system based on unsupervised disentangled representation learning is presented. It is a temporal disentangled variational autoencoder (TDVA) which, mimicking the process of rapid human intuition, using high- or low-dimensional reasoning, finds and models the useful information independently, regardless of the given problem. Specifically, taking samples from the real data distribution representation space, separating them appropriately, and encoding them as separate disentangling dimensions create new examples that the system has not yet dealt with. In this way, first, it utilizes information from potentially inconsistent sources to learn the right representations that can then be broken down into subspace subcategories for easier and simpler categorization, and second, utilizing the latent representation of the model, it performs high-precision estimates of how similar or dissimilar the inputs are to each other, thus recognizing, with great precision and in a fully automated way, the system anomalies.

Security Analysis of the TSN Backbone Architecture and Anomaly Detection System Design Based on IEEE 802.1Qci

With the development of intelligent and connected vehicles, onboard Ethernet will play an important role in the next generation of vehicle network architectures. It is well established that accurate timing and guaranteed data delivery are critical in the automotive environment. The time-sensitive network (TSN) protocol can precisely guarantee the time certainty of the key signals of automotive Ethernet. With the time-sensitive network based on automotive Ethernet being standardized by the TSN working group, the TSN has already entered the vision of the automotive network. However, the security mechanism of the TSN protocol is rarely discussed. First, the security of the TSN automotive Ethernet as a backbone E/E (electrical/electronic) architecture is analyzed in this paper through the Microsoft STRIDE threat model, and possible countermeasures for the security of automotive TSNs are listed, including the security protocol defined in the TSN, so that the TSN security protocol and the traditional protection technology can form a complete automotive Ethernet protection system. Then, the security mechanism per-stream filtering and policing (PSFP) defined in IEEE 802.1Qci is analyzed in detail, and an anomaly detection system based on PSFP is proposed in this paper. Finally, OMNeT++ is used to simulate a real TSN topology to evaluate the performance of the proposed anomaly detection system (ADS). As a result, the protection strategy based on 802.1Qci not only ensures the real-time performance of the TSN but can also isolate individuals with abnormal behavior and block DoS (denial of service) attacks, thus attaining the security protection of the TSN vehicle-based network.