Secure Aggregation for Federated Learning and Distributed Computation
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".
Deadline for manuscript submissions: 31 October 2026 | Viewed by 1705
Special Issue Editors
Interests: information-theoretic security and privacy; secure aggregation; federated learning; private information retrieval (PIR); distributed computing
Special Issue Information
Dear Colleagues,
Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. A core challenge in FL—and, more broadly, in distributed computation (DC)—is secure aggregation, which is ensuring that individual inputs, such as gradients and/or weights of deep neural network (DNN) models, remain confidential during the computation of global functions. While cryptographic methods offer practical solutions, information-theoretic approaches provide unconditional privacy guarantees, making them especially valuable for sensitive or adversarial environments.
Recent advances have applied Shannon-theoretic tools to characterize the fundamental limits of secure aggregation, design provably secure protocols, and analyze robustness under dynamic participation, partial trust, or collusion. These insights not only benefit FL but also inform the broader study of secure multi-party computation and privacy-preserving protocols in distributed learning systems.
Despite the progress, many open challenges remain. Key challenges include the tradeoff between communication and secret key rates, the impact of network topology on security and communication efficiency, and the applicability of information/coding-theoretic methods to adversarial environments. Bridging these gaps requires deeper integration between information theory, distributed optimization, and privacy-preserving machine learning.
This Special Issue welcomes original contributions that explore the use of information-theoretic tools and techniques to enhance the privacy, efficiency, and robustness of secure aggregation in federated learning and distributed computation. Topics of interest include, but are not limited to, the following:
- Fundamental limits and rate region characterizations;
- Protocol design with provable security and robustness guarantees;
- Key generation and coordination schemes;
- Secure aggregation over general network topologies;
- Information-theoretic analysis under realistic system constraints and attack models;
- Experimental validation of theory-inspired secure FL/DC protocols.
Dr. Xiang Zhang
Dr. Mingyue Ji
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
- secure aggregation
- distributed computing
- information-theoretic security
- privacy-preserving machine learning
- secret key generation
- communication efficiency
- linearly separable distributed computation
- robustness
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.
