About the Journal

ISSN: pending registration. Founding Editorial Board: recruitment in progress.

The Journal of Privacy-Preserving AI in Medicine (JFPAI) is a peer-reviewed, open-access journal dedicated to the intersection of privacy-enhancing technologies and artificial intelligence in healthcare and biomedical research.

The digitisation of health data and the rapid expansion of AI-driven medicine create unprecedented opportunities — alongside profound responsibilities. Patient privacy, data sovereignty, and regulatory compliance are not constraints on innovation; they are preconditions for trustworthy AI in healthcare. JFPAI provides a dedicated, rigorous venue for research at this intersection.

Published by Vallensis Publishing in Switzerland — a jurisdiction with a strong tradition of data protection and neutrality — JFPAI brings together researchers in machine learning, clinical informatics, law, and ethics. JFPAI operates under the ethical guidelines of the Committee on Publication Ethics (COPE).

Aims & Scope

JFPAI publishes original research, reviews, and methodological contributions addressing the development, evaluation, and deployment of privacy-preserving AI systems in medical and healthcare contexts. Topics of interest include:

  • Federated learning for clinical and genomic data
  • Differential privacy in biomedical AI
  • Secure multi-party computation in healthcare
  • Homomorphic encryption for health data analysis
  • Synthetic health data generation and validation
  • GDPR, HIPAA, and nFADP compliance in AI systems
  • Privacy risk assessment for clinical AI deployments
  • De-identification and re-identification risk in medical datasets
  • Trusted execution environments for sensitive health data
  • Privacy-preserving genomics and biobank research
  • Audit mechanisms and accountability frameworks
  • Patient data sovereignty and consent management
  • Cross-border health data governance
  • Adversarial attacks on privacy-preserving systems

Out of scope: general privacy research without an AI component, non-healthcare AI privacy, and theoretical cryptography without a healthcare application.