Digital Twin (DT) technologies enable the creation of virtual replicas of learning environments, supporting personalized and real-time educational interventions. However, the integration of Artificial Intelligence (AI) within DT-enabled e-learning introduces critical challenges related to explainability, security, and learner privacy, and lacks a standardized operational framework. This study proposes and validates a comprehensive framework that operationalizes explainability and security for AI models in DT-based e-learning environments, balancing predictive performance, interpretability, and data protection. A quantitative experimental design involving approximately 300 learners evaluates three AI model variants: baseline, explainability-focused, and privacy/ security-enhanced. Predictive modeling employs temporal learner representations with ensemble predictors. Explainability is implemented through post-hoc interpretability techniques such as SHAP and Integrated Gradients, while privacy protection is ensured using Differential Privacy (DP) and Role-Based Access Control (RBAC). Multilevel mixed-effects models are utilized to assess predictive accuracy, explanation fidelity, and privacy guarantees, expressed as $\varepsilon $ -values. Results indicate that incorporating explainability mechanisms increases user trust by approximately 0.8–1.2 points on a Likert scale and enhances explanation fidelity by 25–30%. Integrating privacy controls produces a modest reduction in predictive AUC (up to 8%) but significantly mitigates data leakage risks. The proposed framework offers a standardized and reproducible evaluation suit for the certified deployment of explainable and secure AI systems in DT-enabled e-learning, facilitating transparent trade-offs between performance, interpretability, and privacy.
Digital twins (DTs) are rapidly emerging as foundational enablers of 6G smart cities, offering real time monitoring, predictive analytics, and autonomous control across transportation, energy, healthcare, and industrial domains. Large scale DT adoption faces critical barriers including cybersecurity vulnerabilities, privacy risks, and the absence of standardized orchestration frameworks. This article presents Fed-DTOrch, a comprehensive end to end architecture that integrates federated intelligence, blockchain based audit trails, and AI governance to achieve secure and privacy preserving DT management. The proposed three tier architecture spans IoT and edge devices, domain specific twins, and a city level orchestrator, employing secure federated learning for model updates, lightweight cryptographic authentication, and tamper proof logging. We quantify the DT threat landscape, perform a standards gap analysis across ISO/IEC 27001, 3GPP TS 33.501, ITU-T IoT risk frameworks, and NIST AI RMF, and introduce a 6G ready security framework incorporating federated AI trust metrics, secure synchronization, and explainable AI audits. Cross domain evaluation across five smart city sectors demonstrates 35-60% privacy gain, 40-55% attack mitigation, 28-40% reliability uplift, 26-30% latency reduction, and >85% compliance readiness with <10% overhead. These results provide the first integrated blueprint that combines federated intelligence, blockchain-based auditability, and standards gap analysis to enable secure, standardized, and interoperable DT orchestration for trustworthy 6G ecosystems.
Li Wang, Xiuming Cheng· IEEE Communications Standard...· 2 citations
Digital twin (DT) technology real-time digital counterparts of physical assets has advanced rapidly across critical sectors. In the 6G era, the integration of DTs with ultra-low latency communication, edge intelligence, and artificial intelligence (AI) promises predictive control, enhanced collaboration, and resilient research ecosystems. Yet, this same convergence expands the attack surface: physical tampering, edge compromise, model hijacking, and adversarial AI pose risks that current security standards only partially address. Existing frameworks such as ISO/IEC 27001, 3GPP SA3, ETSI PDL, GDPR, and NIST AI RMF each contribute, but none fully cover end-to-end DT synchronisation, AI governance, or federated research data protection. This article presents a layered predictive security framework for 6G-enabled DTs in university research management and big data protection. The framework integrates provenance anchoring, anomaly detection, risk forecasting, and explainability dashboards with secure network slicing and federated identity management. We map threats to controls, assess coverage of international standards, identify critical gaps, and propose future standardisation directions. A university case study illustrates practical deployment. The work highlights the urgency of harmonising security and AI standards to ensure interoperable, trustworthy, and privacy-preserving DT ecosystems in next-generation communication systems.
The quick development of financial technologies and digital transactions has made fraud detection and regulatory compliance more difficult. This study introduces a Financial Digital Twin with Explainable AI over 6G (FinDT-XAI6G) to enhance real-time fraud detection and compliance monitoring in financial systems. The proposed method leverages the ultra-low latency, high bandwidth, and pervasive intelligence capabilities of 6G networks to enable seamless synchronization between digital twins and real-world financial activities. Common modeling approaches ensure interoperability across financial firms, regulatory bodies, and auditing authorities. Embedded artificial intelligence systems continuously examine vast amounts of transactional data, behavioral patterns, and contextual indications to spot anomalies that could be signs of fraud. Financial firms may now fully and transparently explain automated judgments to regulators thanks to Explainable AI (XAI) modules that enhance interpretability. Blockchain-based audit trails also guarantee data integrity, accountability, and traceability across distributed infrastructures. The integration of 6G connectivity allows for real-time monitoring, cross-border compliance validation, and instant anomaly reporting, even in scenarios with huge data volumes. Comparative studies reveal that our 6G-driven digital twin approach significantly improves detection accuracy, reduces false positives, and expedites compliance verification when compared to traditional methods. Additionally, its scenario modeling capabilities enable the proactive assessment of emerging compliance risks in dynamic regulatory and commercial contexts. Overall, this study demonstrates how financial fraud prevention and compliance assurance in next-generation digital economies can be revolutionized by 6G intelligence-powered standardized, AI-integrated digital twins.
It is argued that both AI and bullshitters are untrustworthy informants, and for similar reasons, it is natural to describe AI’s informational outputs as bullshit, as it signals their distinctive kind of epistemic deficiencies, which they share with bullshit.
Schizophrenia (SZ) is associated with subtle alterations in neural dynamics that are difficult to capture using conventional electroencephalogram (EEG) features. This study introduces a unified deep learning framework that integrates recurrence plots (RP) with wavelet synchrosqueezed transform (WSST) representations into a single fused image modality and leverages attention-enhanced hybrid convolutional–transformer architectures for subject-level classification. Specifically, we propose RP+WSST image fusion combined with convolutional neural network (CNN)–vision transformer (ViT) hybrids (ResNet-18–ViT and EfficientNet-B0–ViT) to jointly model local spatial patterns and global contextual dependencies. Subject-wise 10-fold cross-validation and a strictly isolated hold-out protocol (70/15/15 split) are employed to prevent subject leakage and provide unbiased performance estimates. Compared with single-backbone CNN and ViT models, the proposed hybrid architecture demonstrates competitive generalization. Interpretability is enhanced using appropriate XAI. Gradient-weighted class activation mapping (Grad-CAM) for the CNN branch and Attention Rollout for the ViT branch. The proposed framework is applied to automated SZ detection from resting-state scalp EEG using two independent databases (Warsaw and Atieh schizophrenia EEG (ASEEG)). On the Warsaw dataset, the ResNet-18–ViT hybrid achieved 82.14% accuracy (AUC 83.58%) using Amor-based WSST features. On the ASEEG dataset, performance reached 95.04% accuracy with AUC values above 95%. Channel-wise analysis identified frontal, temporal, and central electrodes as the most discriminative regions, consistent with known SZ-related electrophysiological abnormalities. These findings demonstrate the practical feasibility of deploying the proposed explainable AI (XAI) framework for reliable EEG-based clinical decision support in psychiatric engineering applications.
Sara Bagherzadeh, Mohammadreza Norouzi, Pouya Tolou Kouroshi et al.· Scientific Reports· 0 citations