The growing use of artificial intelligence in the healthcare sector has facilitated the emergence of sophisticated clinical data analytics, but the most critical issues pertain to data privacy, model interpretability, and model trustworthiness. These problems still pose a challenge to its real-world application. This study proposes an interpretation of a deep learning framework for secure clinical data analytics. This proposes a privacy-preserving distributed learning framework in combination with a naturally interpretable model structure. The suggested framework enables parallel training across several healthcare facilities without compromising raw patient information, thereby keeping the data confidential without adversely affecting the analysis. An idea-driven deep learning framework is also presented to produce clinically significant intermediate representations that enable clear, interpretable predictions. Moreover, a new explanation stability mechanism is established to maintain the consistency and reliability of model explanations in distributed environments. To promote clinical safety, the decision module includes uncertainty to enable the system to detect predictions with low confidence and defer them to experts. Massive tests using actual clinical data on patient conditions can be conducted to demonstrate that the framework presented is much more successful than other methods with respect to predictiveness, interpretability, explanation stability, fairness, and calibration. Furthermore, the framework demonstrates that privacy preservation, interpretability, explanation reliability, and clinical usability can be jointly optimized within a unified learning architecture. The findings indicate the effectiveness of the suggested strategy in providing secure, transparent, and reliable clinical decision support, rendering it an appropriate strategy to implement in contemporary healthcare systems.
M. A. Al-Khasawneh, D. Alsekait, K. Alkayid et al.· Scientific Reports· 0 citations
This study aims to guide researchers and practitioners in designing secure, efficient, and privacy-preserving AI systems for healthcare by proposing a structured classification of privacy-preserving methods into four main categories: cryptographic approaches, decentralized learning methods, perturbation-based techniques, and hybrid models.
Chaima Bejaoui, Mohamed Hadded, Hakim Ghazzai et al.· Cluster Computing· 0 citations
The rapid development of the Internet of Things (IoT) has placed considerable pressure on both security and stability in heterogeneous, resource-constrained networks. In such dynamic environments, trust management is a central issue to determine which service providers can be trusted and to combat malicious activity. Although blockchain-based solutions have offered a means for decentralized, tamper-resistant trust management, most rely on classical cryptographic primitives, which are vulnerable to future quantum computing attacks. This study proposes a Quantum-Resistant Blockchain-Based Trust Management (QR-BCTM) framework in which Post-Quantum Cryptographic mechanisms, Permissioned Blockchain Platform, and Fog-assisted Trust Management architecture are combined and utilized in IoT networks. The framework introduces a quantum-aware trust computation model that combines behavioral trust, indirect recommendations, and a cryptographic assurance score quantifying each participant’s compliance with security requirements. Trust evidence is compressed to reduce blockchain storage and communication overhead, while the hierarchical fog-blockchain architecture offloads computationally intensive operations from resource-constrained IoT devices. The performance of the framework has been simulated in the presence of an adversary, including bad-mouthing, ballot-stuffing, on-off behavior, and identity attacks using a Sybil-type mechanism. Trust accuracy, false trust acceptance, communication overhead, and computation cost were measured, and a sensitivity analysis on the trust-weight parameters was performed. The simulation results suggest that QR-BCTM can enhance the accuracy of trust evaluation, mitigate the impact of malicious nodes, and remain scalable and efficient despite the existing cryptographic overhead. Post-quantum digital signatures and formal security analysis provide protection against quantum-era threats and attacks, while classical threats are mitigated through behavioral trust aggregation and recommendation filtering. In summary, QR-BCTM provides a scalable, simulation-validated and quantum-aware framework for trustworthy IoT network operation, offering practical guidelines for future deployment and prototyping.
M. A. Al-Khasawneh, D. Alsekait, K. Alkayid et al.· Scientific Reports· 0 citations