Advancing Privacy-Preserving Federated Learning: Innovative Frameworks and Protocols
A special issue of Entropy (ISSN 1099-4300).
Deadline for manuscript submissions: 31 July 2026 | Viewed by 1899
Special Issue Editors
Interests: applied cryptography; privacy-preserving machine learning; secure data utilization
Interests: privacy enhancing technologies; IoT-big data security and privacy; applied cryptography
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
The increasing demand for data privacy and secure machine learning has fueled interest in federated learning (FL)—a paradigm that enables the training of machine learning models across distributed devices and servers without centralized data collection. This aligns closely with the core themes of Entropy, including information-theoretic security, uncertainty quantification, and the trade-offs among privacy, utility, and efficiency. Despite its promise, federated learning still faces critical challenges in guaranteeing robust privacy in the context of realistic adversarial models. This Special Issue invites high-quality, original research that advances the theoretical foundations and practical implementations of privacy-preserving federated learning, grounded in information theory, entropy-based analysis, and cryptographic mechanisms. We especially welcome interdisciplinary contributions that explore the intersection of machine learning, cryptography, and information theory. Studies that provide measurable security guarantees, resource-efficient protocols, and scalable system designs are of particular interest.
Topics of interest include, but are not limited to, the following:
- Novel protocols for privacy-preserving federated learning;
- Information-theoretic and entropy-based approaches to privacy in FL;
- Practical frameworks combining distributed machine learning and cryptography;
- Integration of homomorphic encryption, secure multiparty computation, and differential privacy in decentralized learning;
- Blockchain and distributed ledger technologies for enhancing trust and accountability in FL;
- Theoretical analysis of privacy–utility trade-offs;
- Secure aggregation and model update strategies;
- System architectures and real-world deployments of privacy-preserving FL;
- Benchmarking, evaluation metrics, and performance analysis of privacy-enhanced federated systems;
The submission of manuscripts that address related advancements in privacy-preserving techniques for other distributed or collaborative learning paradigms is also encouraged. We look forward to receiving your contributions.
Dr. Lihua Wang
Prof. Dr. Rongxing Lu
Guest Editors
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. Entropy 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 2600 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.
Keywords
- federated learning
- privacy preserving
- homomorphic encryption
- differential privacy
- secure multiparty computation
- privacy-enhancing technologies
- distributed AI
- applied cryptography
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
