On the one hand, amid the digital transformation of the financial sector, opportunities have increased for Micro, Small, and Medium Enterprises (MSMEs); on the other hand, challenges remain in technology adaptation and sustainable financial management, especially in a post-crisis era. Thus, given the ongoing push toward strengthening economic resilience, an urgent need arises to examine how far digital financial intelligence may act as a key for the survival and growth of MSMEs. The focus of this study is to examine the impact of digital financial intelligence-the financial literacy, attitude toward financial technology, and capability to use digital financial applications-on MSME economic resilience. Data were collected for the survey using a quantitative approach, which consisted of an online questionnaire administered to 220 MSME actors in Indonesia, who were digital financial services users for a minimum of one year. Participants were selected based on purposive sampling, while data analysis was performed using Structural Equation Modeling (SEM) based on Partial Least Squares (SmartPLS) supported by SPSS, Tableau, and MonkeyLearn. The results of the analysis reveal that all dimensions of digital financial intelligence have a significant relationship with economic resilience, particularly in the tactile domains of crisis adaptation, recovery, and strategic decision-making. Overall, these results now show life documents the need for greater emphasis on literacy and digital readiness as the bedrock of MSME sustainability. This academic contribution is theoretically developing an integrated model of technology and finance while practically implementing the policy implications that would strengthen an inclusive and adaptive MSME digital ecosystem.

Cyber-Physical Systems (CPS) are increasingly deployed in critical infrastructure yet remain vulnerable to adversarial attacks that manipulate sensor data to mislead AI-based decision-making. These threats demand not only high-accuracy detection but also transparency in model reasoning. This study proposes a Hybrid Explainable AI (XAI) Framework that integrates Convolutional Neural Networks (CNN), SHAP-based feature interpretation, and rule-based reasoning to detect adversarial inputs in CPS environments. The framework is tested on two simulation scenarios: industrial sensor networks and autonomous traffic sign recognition. Using datasets of 10,000 samples (50% adversarial via FGSM and PGD), the model achieved an accuracy of 97.25%, precision of 96.80%, recall of 95.90%, and F1-score of 96.35%. SHAP visualizations effectively distinguished between normal and adversarial inputs, and the added explainability module increased inference time by only 8.5% over the baseline CNN (from 18.5 ms to 20.1 ms), making it suitable for real-time CPS deployment. Compared to prior methods (e.g., CNN + Grad-CAM, Random Forest + LIME), the proposed hybrid framework demonstrates superior performance and interpretability. The novelty of this work lies in its tri-level integration of predictive accuracy, explainability, and rule-based logic within a single real-time detection system—an approach not previously applied in CPS adversarial defense. This research contributes toward trustworthy AI systems that are robust, explainable, and secure by design.