Advanced Machine Learning for Secure Data Processing

Dear Colleagues,

In an era defined by pervasive data collection and intelligent automation, the ability to learn from data securely and responsibly has become a central challenge in Artificial Intelligence. As Machine Learning systems play a growing role in healthcare diagnostics, financial forecasting, critical infrastructure management, and consumer technologies, their decisions increasingly affect individuals, institutions, and society at large. However, these advances also heighten concerns related to privacy leaks, adversarial manipulation, and insufficient transparency in model behaviour. Thus, ensuring privacy in ML-driven systems has become critical for gaining public trust and complying with data regulations. In this context, delivering scalable, efficient, and secure ML services while preserving privacy remains challenging due to issues such as computational complexity, data heterogeneity, real-time constraints, and trade-offs in model accuracy.

Achieving trustworthy and privacy-preserving intelligence requires integrating advances from Machine Learning, cryptography, security, and distributed computing. This includes developing algorithms and systems capable of extracting value from sensitive, distributed, and regulated datasets while safeguarding confidentiality, integrity, and ethical compliance, as well as deploying specific techniques such as secure multi-party computation, homomorphic encryption, differential privacy, and trusted execution environments to protect both ML models and sensitive data throughout the ML lifecycle. By fostering collaboration across these domains, this Special Issue seeks to advance the foundational and applied research necessary to realize secure and responsible AI systems that balance utility, accountability, and user sovereignty.

Call for Papers

This Special Issue focuses on advanced Machine Learning methods that enable secure, privacy-preserving, and verifiable data processing across distributed and sensitive environments. We invite contributions that address challenges at the intersection of learning efficiency, data protection, and system trustworthiness.

Topics of interest include, but are not limited to, the following:

• Federated and split learning;
• Privacy-preserving gossip learning;
• Privacy in decentralized AI;
• Decentralized frameworks supporting user-controlled data ownership;
• Privacy-perserving decentralized IR and learning over personal data stores;
• Secure multi-party computation;
• Differential privacy mechanisms;
• Homomorphic encryption and privacy-preserving inference;
• Trusted execution environments;
• Robust and adversarial learning;
• Verifiable, explainable, and auditable AI;
• Hybrid paradigms balancing security, efficiency, and scalability;
• Secure data governance and access-control-aware learning.

Dr. Mohamed Ragab
Dr. Nouh Elmitwally
Dr. Faisal Saeed
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly 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 2400 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.