Privacy Computing and Federated Learning

Dear Colleagues,

In an era of unprecedented data generation and increasing privacy concerns, the intersection of privacy-preserving technologies and distributed machine learning has emerged as a critical research frontier. Privacy computing and federated learning represent paradigm shifts in how we approach data analysis, model training, and collaborative intelligence while safeguarding individual privacy and data sovereignty. Recent regulatory frameworks, including the General Data Protection Regulation (GDPR), the California Consumer Privacy Act (CCPA), and similar legislation worldwide, have intensified the need for privacy-preserving computational methods.

Privacy computing encompasses a broad spectrum of technologies, including secure multi-party computation, homomorphic encryption, differential privacy, trusted execution environments, and zero-knowledge proofs. These technologies collectively enable computation on encrypted or distributed data while maintaining confidentiality. Federated learning, pioneered as a solution for training machine learning models across decentralized devices, has evolved into a comprehensive framework addressing challenges in healthcare, finance, telecommunications, smart cities, and numerous other domains.

This Special Issue invites papers presenting novel theoretical frameworks, innovative algorithms, practical implementations, empirical studies, and real-world applications that advance the state-of-the-art in privacy computing and federated learning. Potential topics include, but are not limited to:

• Federated learning algorithms and optimization techniques;
• Differential privacy in distributed machine learning;
• Secure multi-party computation and homomorphic encryption;
• Privacy-preserving data mining and analytics;
• Blockchain-enabled federated learning;
• Vertical and horizontal federated learning architectures;
• Privacy attacks and defense mechanisms in federated systems;
• Communication-efficient federated learning;
• Personalized federated learning and model customization;
• Federated learning for edge computing and IoT;
• Privacy-preserving deep learning;
• Trusted execution environments for privacy computing;
• Privacy threat analysis in AI agent systems;
• Privacy-preserving multi-agent learning and collaboration;
• Secure communication protocols for AI agent ecosystems;
• Fairness, accountability, and transparency in federated systems;
• Applications in healthcare, finance, and smart cities;
• Benchmarking and evaluation frameworks.

Authors are invited to contribute their original and unpublished works. We welcome research and review papers alike. Research papers presenting preliminary and proof-of-concept results are also welcome. Authors may also submit extended versions of their conference papers. However, the authors of such papers should make significant improvements/extensions to their conference paper, and the details of these improvements/extensions should be clearly outlined in the cover letter accompanying the paper's submission.

Dr. Yong-Feng Ge
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• privacy computing
• federated learning
• differential privacy
• secure multi-party computation
• homomorphic encryption
• privacy-preserving algorithms
• machine learning security