Security and Privacy for Artificial Intelligence Systems

Dear Colleagues,

Artificial intelligence (AI) is increasingly becoming a foundational component of modern electronic systems, enabling intelligent sensing, decision-making, and autonomous operation across applications such as edge computing, cyber–physical systems, robotics, healthcare, and large-scale distributed infrastructures. As AI transitions from centralized model development to real-world deployment, new challenges emerge in ensuring security, privacy, reliability, and trustworthiness across the entire AI system stack. Vulnerabilities may arise not only from learning algorithms but also from system architectures, hardware platforms, data pipelines, communication protocols, and deployment environments.

This Special Issue, “Security and Privacy for Artificial Intelligence Systems”, aims to advance research that addresses security and privacy challenges from a holistic, cross-layer perspective. The focus of this topical collection includes:

1. Developing secure and privacy-preserving AI methodologies spanning training, inference, and adaptation;
2. Designing trustworthy AI system architectures across cloud, edge, and collaborative environments;
3. Enabling secure deployment through hardware–software co-design and system-level innovations.

The interested topics include, but are not limited to, adversarial robustness and model security, privacy-preserving and distributed learning (e.g., federated and collaborative intelligence), secure edge AI systems, trustworthy and interpretable AI, secure data management and communication for AI pipelines, system reliability and verification, and privacy-aware hardware and architecture design. Contributions that bridge multiple layers of the AI stack—from algorithms and models to systems and hardware—are particularly encouraged.

The existing literature has largely focused on isolated aspects of AI security or privacy at the algorithmic level. However, real-world AI deployments demand integrated solutions that jointly consider model behavior, system constraints, hardware efficiency, and operational environments. This Special Issue seeks to supplement current research by promoting end-to-end perspectives that unify security and privacy across the lifecycle of AI systems. By fostering interdisciplinary collaboration among researchers in computer systems, machine learning, and cybersecurity, this collection aims to accelerate the development of secure, privacy-aware, and trustworthy AI systems for next-generation intelligent systems.

We welcome original research articles, review papers, and application-driven studies that contribute novel theories, systems, and practical deployments advancing secure and privacy-preserving AI systems.

Dr. Jingwei Sun
Dr. Ang Li
Dr. Huanrui Yang
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. 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.

• secure artificial intelligence
• trustworthy AI systems
• adversarial machine learning
• AI system security