The AIAS project continues to strengthen its scientific and technological impact with the publication of three new peer-reviewed research papers, presented at leading international conferences and addressing critical challenges at the intersection of artificial intelligence, cybersecurity, and resilient digital infrastructures.
Together, these publications reflect the AIAS vision of advancing secure, trustworthy, and resilient AI-enabled systems, spanning digital ecosystems, healthcare, and adversarial AI defense.
Real-Time Digital Ecosystems with Virtual Personas and Digital Twins
Presented at ARES 2025 – Springer Nature
The first publication, “Real-Time Digital Ecosystems: Integrating Virtual Personas and Digital Twins Through Microservices”, introduces a scalable and interoperable architecture for real-time digital ecosystems. By leveraging a microservices-based design, the work enables seamless integration of Virtual Personas and Digital Twins, addressing key challenges in real-time data processing, availability, and system resilience.
This research contributes to AIAS by demonstrating how distributed, AI-driven architectures can support complex cyber-physical systems while maintaining robustness and adaptability across smart environments.
Secure and Resilient Digital Health Ecosystems
Presented at IEEE BlackSeaCom 2025
The second paper, “Cross-Vertical Integration of AI, Blockchain, and IoT for Secure and Resilient Digital Health Ecosystems”, focuses on one of the most sensitive and critical application domains: digital health. The proposed cross-vertical architecture combines AI, Blockchain, and IoT technologies to enhance data integrity, interoperability, and system resilience in distributed healthcare environments.
By addressing trust, security, and reliability at both architectural and operational levels, this work aligns closely with the AIAS mission to enable trustworthy AI solutions in high-impact, real-world sectors.
Detecting Adversarial AI Attacks with XAI and Deception Mechanisms
AI for Cybersecurity
The third publication, “Adversarial AI Attack Detection: A Novel Approach Using Explainable AI and Deception Mechanisms”, tackles the growing threat of adversarial attacks against AI systems. The paper proposes an innovative detection framework that combines adversarial training, Explainable AI (XAI), and deception techniques, including honeypots and digital twins.
By enabling real-time, interpretable detection of adversarial behavior and capturing attacker strategies through decoy systems, this work delivers practical tools for strengthening AI resilience—directly supporting the AIAS focus on AI for Cybersecurity and Cybersecurity for AI.
A Unified Contribution to Trustworthy AI
Collectively, these three publications highlight the multidisciplinary strength of the AIAS project, demonstrating how secure architectures, cross-technology integration, explainability, and deception-based defense mechanisms can be combined to protect AI systems across diverse domains.
Through continued research, collaboration, and dissemination, AIAS remains committed to shaping the future of secure, resilient, and trustworthy AI technologies for industry, society, and critical infrastructures.