ENIGMA: An explainable digital twin security solution for cyber–physical systems

Digital Twins (DTs), being the virtual replicas of their physical counterparts, share valuable knowledge underlying processes and act as data acquisition dissemination sources to Cyber–Physical System (CPS). Moreover, without obstructing ongoing operations, DTs also provide an assessment platform for evaluating operational behavior security CPS. Therefore, they become a potential source breaches broad attack surface attackers launch covert attacks. To detect mitigate loopholes in DTs, one solutions is leverage gamification approach that can assess level while providing analysts with controlled supportive training environment. Artificial Intelligence/Machine Learning (AI/ML)-based approaches complement idea orchestration automation approach. However, AI/ML-based are generally constrained by lack transparency AI which results less confidence decisions made models. address explainable challenges this article proposes called sEcuriNg dIgital twins through GaMification Approach (ENIGMA). While leveraging offensive platform, ENIGMA provides gaming scenarios DTs’ train analysts. The game players within humans (the attacker team) agents defender team). Furthermore, supported eXplainable (XAI)-based DT model explains based on SHAP values vectors team, i.e., agent. illustrate contribution different features towards predicting outcome vectors. This explanation help take measures reasoned trustworthy decisions. Finally, experimental validation has been carried out demonstrate viability ENIGMA.