AI-Driven Cybersecurity for Intelligent and Connected Systems

Dear Colleagues,

We are pleased to invite you to contribute to this Special Issue on AI-driven cybersecurity for intelligent and connected systems. Intelligent and connected systems, including the Internet of Things, cyber–physical systems, edge and mobile devices, and increasingly autonomous AI-driven infrastructures, are becoming a core part of everyday life and critical operations. Their scale and heterogeneity make them attractive and vulnerable targets, since data is collected, processed, and shared across many resource-constrained and often untrusted nodes. Artificial Intelligence, and in particular Machine Learning and Large Language Models, is increasingly used both to enhance the security of these systems and to introduce new risks that must be understood and mitigated.

This Special Issue aims to collect original contributions on AI-driven approaches to securing intelligent and connected systems, from classical IoT and cyber–physical infrastructures to emerging AI-native architectures built on generative models and autonomous agents. This is closely aligned with the scope of Future Internet, which covers the technologies, protocols, and applications shaping the future of connected systems, including the Internet of Things, network security, and intelligent infrastructures. We welcome contributions on how AI, and particularly federated and distributed learning, can support privacy-preserving anomaly detection, intrusion detection, and threat response across connected devices without centralizing sensitive data. We are equally interested in the security of the AI components themselves, including their robustness to backdoor attacks, poisoning, adversarial manipulation, and unlearning-related vulnerabilities, and in how these risks propagate when models are deployed, fine-tuned, or trained collaboratively across many connected and often mutually untrusting parties. Contributions addressing the growing role of generative and agentic AI in connected environments, including the security of LLM-based agents interacting with IoT and edge infrastructures, are also welcome.

In this Special Issue, original research articles and reviews are welcome. Research areas may include (but are not limited to) the following:

• Federated and distributed learning for privacy-preserving security in IoT and connected systems
• Attacks and defenses in federated and collaboratively trained models
• Privacy-preserving anomaly and intrusion detection using homomorphic encryption, differential privacy, or secure aggregation
• Adversarial robustness of AI models deployed on edge and connected devices
• Security and privacy risks of machine unlearning in connected and federated settings
• Blockchain-assisted federated learning for trust and security in IoT ecosystems
• Security of generative and agentic AI systems interacting with IoT and cyber-physical infrastructures
• Explainable AI for security analysis and decision-making in intelligent connected systems
• Label and membership inference attacks in vertical and horizontal federated learning
• Case studies and real-world deployments of AI-driven security in smart homes, smart cities, and industrial IoT

This Special Issue will provide novel contributions that will drive cutting-edge research, leading to more secure and trustworthy intelligent and connected systems, leveraging advances in federated learning, privacy-preserving AI, and generative and agentic models. Quality submissions from academia and industry are welcome.

Dr. Marco Arazzi
Dr. Antonino Nocera
Dr. Serena Nicolazzo
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. Future Internet 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 1800 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.