Cybersecurity Solutions for Intelligent Systems

Dear Colleagues,

Intelligent systems—such as AI-driven decision-making platforms, autonomous agents, cyber–physical systems and large-scale data-centric applications—are increasingly embedded in critical domains including healthcare, transportation, finance, education and national infrastructure. While these systems deliver unprecedented efficiency and autonomy, they also introduce novel cybersecurity vulnerabilities arising from data-driven learning, distributed intelligence, model complexity and human–AI interaction. Traditional security mechanisms are often insufficient to address the evolving threat landscape posed by adversarial attacks, privacy leakage, model exploitation and system-level failures in intelligent environments.

This Special Issue, “Cybersecurity Solutions for Intelligent Systems,” aims to advance research that systematically address security, privacy, trust and resilience challenges in modern intelligent systems.

1. Focus
   The primary focus of this Special Issue is on innovative cybersecurity solutions tailored for intelligent systems, emphasizing AI-aware, data-centric and system-level security mechanisms. The issue prioritizes methods that protect intelligent models, data pipelines and autonomous decision processes against emerging cyber threats.
2. Scope
   The scope encompasses both theoretical and applied research related to cybersecurity in intelligent systems, including, but not limited to, the following:

• Security and privacy of machine-learning and deep-learning models
• Adversarial machine learning and robust AI defenses
• Federated learning security, privacy preservation and unlearning
• Secure autonomous and cyber–physical systems
• Trustworthy AI, explainability and model accountability
• Intrusion detection and threat intelligence using AI
• Secure edge, IoT and distributed intelligent systems
• Data poisoning, model inversion, membership inference and defense mechanisms
• Human-centered security and ethical considerations in intelligent systems

3. Relationship to and Contribution Beyond Existing Literature

This Special Issue supplements and extends prior research by:

• Integrating AI-specific threat models with system-level cybersecurity frameworks
• Advancing research beyond detection toward prevention, mitigation, recovery and unlearning
• Emphasizing trust, explainability and ethical resilience alongside technical robustness
• Consolidating emerging solutions across domains such as federated learning, autonomous systems and edge intelligence

Dr. Pretom Roy Ovi
Prof. Dr. Aryya Gangopadhyay
Dr. Sergei Chuprov
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.