Blockchain-Enabled Federated Learning for Privacy and Security

The book "Blockchain-Enabled Federated Learning for Privacy and Security" explores the integration of blockchain technology and federated learning to address critical challenges in healthcare data sharing. With the rise of electronic health records, medical imaging, IoMT devices, and genomics, safeguarding patient privacy while enabling collaborative AI has become essential. Blockchain provides decentralization, immutability, and trust, while federated learning ensures model training without exposing raw data. Together, they form a privacy-preserving, auditable, and scalable framework for healthcare AI. The book covers fundamentals, system architectures, cryptographic techniques, and performance trade-offs, along with real-world case studies in cancer research, IoMT, and COVID-19 diagnosis. It highlights regulatory and ethical considerations such as GDPR, HIPAA, and India's DPDP Act, and proposes future research in quantum integration, explainable AI, fairness-aware FL, and governance through smart contracts. This comprehensive guide serves researchers, healthcare professionals, and policymakers in building secure, transparent, and patient-centric healthcare ecosystems.

Autorentext

Prof. M. Sukanya is an Assistant Professor in the Data Science Dept. at Holy Cross College (Autonomous), Tiruchirappalli. Ms. A. Kavipriya is serving as an Assistant Professor in the Department of Artificial Intelligence and Machine Learning at Holy Cross College (Autonomous), Tiruchirappalli.

Klappentext

The book "Blockchain-Enabled Federated Learning for Privacy and Security" explores the integration of blockchain technology and federated learning to address critical challenges in healthcare data sharing. With the rise of electronic health records, medical imaging, IoMT devices, and genomics, safeguarding patient privacy while enabling collaborative AI has become essential. Blockchain provides decentralization, immutability, and trust, while federated learning ensures model training without exposing raw data. Together, they form a privacy-preserving, auditable, and scalable framework for healthcare AI. The book covers fundamentals, system architectures, cryptographic techniques, and performance trade-offs, along with real-world case studies in cancer research, IoMT, and COVID-19 diagnosis. It highlights regulatory and ethical considerations such as GDPR, HIPAA, and India's DPDP Act, and proposes future research in quantum integration, explainable AI, fairness-aware FL, and governance through smart contracts. This comprehensive guide serves researchers, healthcare professionals, and policymakers in building secure, transparent, and patient-centric healthcare ecosystems.