Securing Cyber-Physical Systems Through Blockchain-Based Digital Twins and Threat Intelligence
release_fstlushfd5h2nhb75sfbs45ila
by
Sabah Suhail, Raja Jurdak, Raimundas Matulevičius, Choong Seon Hong
2021
Abstract
The proliferation of digitization and complexity of connectivity in
Cyber-Physical Systems (CPSs) calls for a mechanism that can evaluate the
functionality and security of critical infrastructures. In this regard, Digital
Twins (DTs) are revolutionizing the CPSs. Driven by asset-centric data, DTs are
virtual replicas of physical systems that mirror every facet of a product or
process and can provide actionable insights through monitoring, optimization,
and prediction. Furthermore, replication and simulation modes in DTs can
prevent and detect security flaws in the CPS without obstructing the ongoing
operations of the live system. However, such benefits of DTs are based on an
assumption about data trust, integrity, and security. Data trustworthiness is
considered to be more critical when it comes to the integration and
interoperability of multiple components or sub-components among different DTs
owned by multiple stakeholders to provide an aggregated view of the complex
physical system. Moreover, analyzing the huge volume of data for creating
actionable insights in real-time is another critical requirement that demands
automation. This article focuses on securing CPSs by integrating Artificial
Intelligence (AI) and blockchain for intelligent and trusted DTs. We envision
an AI-aided blockchain-based DT framework that can ensure anomaly prevention
and detection in addition to responding against novel attack vectors in
parallel with the normal ongoing operations of the live systems. We discuss the
applicability of the proposed framework for the automotive industry as a CPS
use case. Finally, we identify challenges that impede the implementation of
intelligence-driven architectures in CPS.
In text/plain
format
Archived Files and Locations
application/pdf 496.3 kB
file_5weblta6vjdcvmaq3dnupklnha
|
arxiv.org (repository) web.archive.org (webarchive) |
2105.08886v1
access all versions, variants, and formats of this works (eg, pre-prints)