Parallel anomaly detection algorithm for cybersecurity on the highspeed train control system

Abstract

<abstract> <p>With the rapid development of the high-speed train industry, the high-speed train control system has now been exposed to a complicated network environment full of dangers. This paper provides a speculative parallel data detection algorithm to rapidly detect the potential threats and ensure data transmission security in the railway network. At first, the structure of the high-speed train control data received by the railway control center was analyzed and divided tentatively into small chunks to eliminate the inside dependencies. Then the traditional threat detection algorithm based on deterministic finite automaton was reformed by the speculative parallel optimization so that the inline relationship's influences that affected the data detection order could be avoided. At last, the speculative parallel detection algorithm would inspect the divided data chunks on a distributed platform. With the help of both the speculative parallel technique and the distributed platform, the detection deficiency for train control data was improved significantly. The results showed that the proposed algorithm exhibited better performance and scalability when compared with the traditional, non-parallel detection method, and massive train control data could be inspected and processed promptly. Now it has been proved by practical use that the proposed algorithm was stable and reliable. Our local train control center was able to quickly detect the anomaly and make a fast response during the train control data transmission by adopting the proposed algorithm.</p> </abstract>

Edge Intelligence-Assisted Asymmetrical Network Control and Video Decoding in the Industrial IoT with Speculative Parallelization

“…To make the boundary between NALUs obvious and speed up the decoding rate in edge servers in IIoT, we intend to use the speculative parallelization technique to enable parallel decoding. As a mature parallel accelerating tool on multi-core platforms, threadlevel speculation (TLS) has emerged to empower thread-level speculative parallelization with domain knowledge [18]. By tolerating inter-unit dependencies, TLS allows threads or computations (that were thought to be non-parallel) to proceed in the speculative parallelization, thereby gaining the parallelization when speculation succeeds.…”

“…More precisely, AVS-M has to sequentially analyze the contents in NALUs and then merge the analytical results. Nevertheless, when the large data spans multiple NALUs (e.g., in the industry monitoring), this type of NALU sequential analyzing and decoding method could not fully utilize the computing resources, incurring a large processing delay and failing to make a real-time operational decision [18], and thus not adapt to rapidly changing industrial field situations. As such, the simultaneous speculative parallelization has been utilized to speed up the decoding efficiency [19][20][21].…”

“…Nevertheless, traditional serial decoding methods are limited by the video coding order, and cannot decode the video data in parallel, resulting in low decoding efficiency and overlarge processing delay. Thus, boosted by recent advents in both edge computing and IIoT applications, and to track the industrial environment, we try to introduce the speculative parallelization technique [18], rather than use the traditional NALU sequential analyzing method, to save the surveillance video processing and decoding delay in the industrial field. In particular, with advances in mobile chips and compelling techniques, the speculative parallel decoding can be promoted to some extent, thereby significantly improving the performance of AVS-M in terms of decoding efficiency.…”