The integration of Digital Twin (DT) and Internet of Military Things (IoMT) technologies is a key enabler of the Defense 4.0 paradigm, supporting real-time monitoring and decision-making in cyber–military environments. This paper proposes a Game-Theoretic Digital Twin (GT–DT) framework for mission risk assessment and adaptive decision optimization under adversarial and data-intensive operational conditions. The framework leverages a DT-enabled sensing network to capture heterogeneous battlefield data, which is processed using a Bayesian probabilistic model within a fog–cloud architecture to estimate the Probability of Mission Success (PoMS). A two-player game-theoretic model is formulated between the Defender and the Attacker to derive a unified Mission Risk Assurance Index (MRAI), enabling equilibrium-based strategic decision-making. The Defender aims to minimize mission risk through optimal resource allocation and adaptive countermeasures, while the Attacker attempts to exploit system vulnerabilities to disrupt mission objectives. The framework is validated through scenario-driven simulations, including cyber intrusion and UAV-based surveillance operations, demonstrating its practical applicability in representative mission contexts. Experimental results indicate improved performance over conventional approaches, achieving a mean decision delay of 123.60 ms, precision of 93.07%, specificity of 91.67%, sensitivity of 92.07%, decision-making accuracy of 96.92%, and overall reliability of 91.97%. The proposed GT–DT framework provides a focused, data-driven solution for real-time mission risk assessment and decision support in complex cyber–military operations.
Aljumah et al. (Mon,) studied this question.