Symmetry-Aware Artificial Intelligence for Cybersecurity and Smart Healthcare

Dear Colleagues,

Artificial intelligence has emerged as a powerful paradigm for addressing complex challenges in cyberspace security and healthcare. By integrating machine learning, deep learning, large language models, intelligent agents, federated learning, and trustworthy decision-making mechanisms, AI technologies enable automatic threat detection, intelligent risk assessment, medical image analysis, clinical decision support, privacy protection, and personalized healthcare services. In particular, symmetry-related principles, such as structural symmetry, behavioral consistency, feature invariance, data balance, model robustness, and adversarial symmetry, provide valuable theoretical and methodological foundations for designing reliable, interpretable, and secure AI systems.

In the field of cybersecurity, AI has shown great potential in detecting malware, identifying network intrusions, discovering software vulnerabilities, analyzing encrypted traffic, supporting security operation centers, and enabling autonomous cyber defense. However, the increasing complexity of cyberattacks, the emergence of adversarial samples, data imbalance, model drift, and the lack of explainability still pose significant challenges to the practical deployment of AI-based security systems. Symmetry-aware learning, invariant representation, graph-based reasoning, and robust optimization can help improve the generalization, reliability, and resilience of intelligent cybersecurity models in dynamic and adversarial environments.

In the healthcare domain, AI-driven methods have been widely applied to medical image segmentation, disease diagnosis, multimodal health data analysis, drug discovery, patient monitoring, and medical decision support. Medical data often exhibit important structural, spatial, temporal, and physiological symmetry properties, such as bilateral organ symmetry, anatomical regularity, temporal consistency in disease progression, and balanced representation across patient populations. Leveraging these symmetry characteristics can enhance the accuracy, interpretability, fairness, and clinical reliability of AI models. At the same time, healthcare AI systems must address key issues such as data privacy, model transparency, cross-institutional collaboration, and trustworthy deployment.

To address these challenges, this Special Issue aims to bring together researchers and practitioners working on artificial intelligence, cybersecurity, healthcare, privacy protection, and symmetry-related modeling. We welcome original research articles and review papers that explore new theories, methods, algorithms, systems, and applications of AI for solving cybersecurity and medical problems. Contributions may focus on symmetry-aware AI models, trustworthy and explainable learning, privacy-preserving computation, intelligent agents, graph neural networks, large language models, federated learning, adversarial robustness, and real-world applications in cyber defense and smart healthcare.

This Special Issue is intended to provide a platform for interdisciplinary research that bridges artificial intelligence, cyberspace security, medical intelligence, and symmetry-based analysis. We particularly encourage studies that combine theoretical innovation with practical validation, and that demonstrate how AI can improve the security, reliability, efficiency, and trustworthiness of complex cyber and medical systems.

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

1. Symmetry-aware artificial intelligence models for cybersecurity and healthcare;
2. AI-based network intrusion detection, malware analysis, and cyber threat intelligence;
3. Intelligent vulnerability detection, software security analysis, and automated penetration testing;
4. Large language models and intelligent agents for cyber defense and security operations;
5. Graph neural networks and knowledge graphs for attack reasoning, risk assessment, and medical knowledge modeling;
6. Adversarial machine learning, robust AI, and trustworthy learning in cyber and medical scenarios;
7. Privacy-preserving AI, federated learning, and secure multi-party computation for sensitive data analysis;
8. AI-based medical image analysis, disease diagnosis, and clinical decision support;
9. Symmetry, invariance, and structural priors in medical imaging and biomedical data analysis;
10. Multimodal AI for integrating network traffic, logs, images, texts, electronic health records, and sensor data;
11. Explainable and interpretable AI for cybersecurity and healthcare applications;
12. Data imbalance, anomaly detection, and rare-event learning in cyberattack detection and disease diagnosis;
13. Lightweight and edge-deployable AI models for secure IoT, Internet of Medical Things, and mobile healthcare;
14. Human–AI collaboration for security analysis, medical decision-making, and emergency response;
15. Evaluation frameworks, benchmark datasets, and real-world applications of AI in cyberspace security and smart healthcare.

Dr. Yang Xiao
Dr. Fengyu Wang
Guest Editors

Dr. Hao Sun
Guest Editor Assistant

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. Symmetry 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 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.

• artificial intelligence
• cyberspace security
• smart healthcare
• symmetry-aware learning
• trustworthy AI