Skip to content
Open access

Hybrid Explainable AI, Federated Learning, and Blockchain Framework for Trustworthy Cybersecurity

Jun 2026 · International Journal for Research in Applied Science and Engineering Technology · Vol 14, pp. 3372-3380 · 0 citations

TL;DR

The proposed hybrid framework offers an effective solution for secure and trustworthy next-generation cybersecurity in IoT, cloud, and enterprise environments and demonstrates improved threat detection performance, enhanced privacy preservation, greater transparency, and stronger resilience against adversarial attacks.

Abstract

The increasing adoption of cloud computing, the Internet of Things (IoT), and distributed networks has intensified cybersecurity challenges, requiring intelligent, secure, and privacy-preserving threat detection mechanisms. This paper proposes a hybrid framework that integrates Explainable Artificial Intelligence (XAI), Federated Learning (FL), and Blockchain to develop a trustworthy cybersecurity system. Federated Learning enables collaborative model training without sharing sensitive data, blockchain ensures secure and tamper-resistant verification of model updates, and XAI techniques such as SHAP and LIME provide transparent explanations for cyber threat predictions. The proposed framework is evaluated using benchmark intrusion detection datasets based on metrics including accuracy, precision, recall, F1-score, blockchain latency, and communication overhead. The results demonstrate improved threat detection performance, enhanced privacy preservation, greater transparency, and stronger resilience against adversarial attacks. The proposed hybrid framework offers an effective solution for secure and trustworthy next-generation cybersecurity in IoT, cloud, and enterprise environments.

Read PDF

Similar papers

Aug 2026

A Secure Federated Learning and Blockchain Framework for E-Health Threat Detection

The proposed framework effectively integrates encryption, federated intrusion detection, explainable artificial intelligence, and blockchain security to enhance privacy, transparency, and reliability in IoMT healthcare networks.

P. Banupriya, K. Vanitha · 0 citations
Aug 2026

BELS-IoT: A Blockchain-Integrated Ensemble Learning Framework for Secure and Trustworthy IoT Device Protection

BELS-IoT is proposed, a novel decentralized protection architecture that integrates a cryptocurrency-based blockchain layer with a multi-layer ensemble learning engine that rewards honest behavior and penalizes malicious activities while maintaining privacy through federated learning with blockchain-verified reputation scores.

Anwar Kalghoum, Leila Azouz Saidane · 0 citations
Review Open access Aug 2026

Blockchain-Driven Cybersecurity Framework for Smart Digital Ecosystems

Overall, this review demonstrates that blockchain-based cybersecurity frameworks provide a secure, transparent, and resilient foundation for protecting smart digital environments against increasingly sophisticated cyber threats while supporting trustworthy and scalable digital transformation.

M. Kayla, Crispinus Ode, Marion Sanaipei · 0 citations
Open access Aug 2026

A trust-aware privacy-preserving federated learning framework for secure threat intelligence sharing using blockchain

Collaborative threat intelligence sharing has become essential for defending distributed enterprise and smart city infrastructures against increasingly sophisticated cyber threats. However, organizations remain reluctant to share raw security data due to privacy, regulatory, and trust concerns. Federated Learning (FL) has emerged as a promising solution by enabling collaborative model training without exposing local data. Nevertheless, traditional FL-based intrusion detection frameworks remain vulnerable to model poisoning, Byzantine attacks, and lack transparent accountability mechanisms for cross-organization collaboration. This paper proposes an engineering framework for privacy-preserving federated threat intelligence sharing that integrates trust-aware robust aggregation with blockchain-based integrity anchoring. The proposed architecture introduces a dynamic reputation mechanism that evaluates participant reliability across communication rounds and assigns adaptive aggregation weights to mitigate malicious updates. To enhance transparency and non-repudiation, model update hashes and trust evolution records are anchored on a permissioned blockchain through smart contracts, ensuring immutable auditability without exposing sensitive parameters. The framework is evaluated using a non-IID partition of the ToN-IoT dataset across multiple simulated organizations. Experimental results demonstrate significant robustness improvements under adversarial environments. Under Byzantine attacks with 20% malicious clients, the proposed trust-aware aggregation mechanism achieves approximately 95% Accuracy and 95% F1-macro, compared with approximately 89% obtained using conventional FedAvg. Furthermore, under highly adversarial conditions involving 40% malicious participants, the proposed framework maintains approximately 95% Accuracy and F1-macro, whereas FedAvg degrades to approximately 78% Accuracy and 77% F1-macro. These results confirm the effectiveness of the proposed trust-aware aggregation mechanism in mitigating malicious updates while preserving stable convergence and reliable intrusion detection performance.

Mehdi Houichi, Faouzi Jaidi, Adel Bouhoula · 0 citations
Review Open access Aug 2026

Blockchain-Enabled Trustworthy Federated Learning for Privacy- Preserving Artificial Intelligence: Consensus Protocols, Cryptographic Security, Scalability, and Real-World Deployment

Federated learning helps in collaborative training of AI models without transmitting raw data, and hence it is an exciting approach for privacy-conscious applications. Nonetheless, traditional federated learning still suffers from weaknesses such as susceptibility to attacks from malicious actors, susceptibility to model poisoning, single point of coordination, lack of transparency, and scalability issues. Blockchain technology provides a decentralized method of trusting which can help in enhancing the security, accountability, and integrity of federated learning. This paper presents a comprehensive analysis of blockchain based trustworthy federated learning through the examination of the role played by consensus algorithms, cryptographic security techniques, scalability approaches, and deployment strategies. A systematic literature review was conducted using recently published papers from peer-reviewed sources. The selected papers were analyzed using inclusion and exclusion criteria to reveal technological advancements, deployment problems, and practical applications. Consensus methods, which include Proof of Stake, Practical Byzantine Fault Tolerance, Delegated Proof of Stake, and hybrid versions, illustrate various tradeoffs between security, processing speed, latency, and energy utilization. Encryption algorithms like homomorphic encryption, secure multiparty computation, differential privacy, and digital signatures offer added value to privacy and resilience against malicious activity. The review presents several shortcomings concerning communication overheads, blockchain storage expansion, delays in the consensus process, interoperability, and resource-limited edge computing nodes. Recent innovations, such as lightweight consensus, hierarchical blockchain structures, off-chain storage, and adaptive communication models, reveal high prospects in addressing those shortcomings. This research reveals that federated learning by blockchain is a robust and scalable platform to enable privacy-preserving artificial intelligence in healthcare, finance, IoT, smart city, and industrial applications.

Arthi D, R Anand, Palaniappan Sambandam et al. · 0 citations