Aims and Scope

FMDB Transactions on Sustainable Intelligence and Security (FTSIS) is a peer-reviewed journal dedicated to publishing original research articles, reviews, and communications that deliver substantial new insights across fields involving artificial intelligence and cyber security. As AI increasingly underpins digital services, critical infrastructure, and decision-making workflows, it introduces new attack surfaces, operational risks, and governance challenges. At the same time, AI has become a key enabler for improving prevention, detection, prediction, response, and resilience against fast-evolving cyber threats. FTSIS covers the full spectrum of AI research, spanning AI applications, techniques, theory, ethics, and planning, with particular emphasis on robust and secure deployment in modern computing environments such as cloud, mobile, IoT, and cyber–physical systems. FTSIS welcomes experimental and theoretical work presented with sufficient methodological and implementation detail to support reproducibility and practical adoption. Authors are encouraged to provide full experimental details, including datasets, evaluation protocols, and relevant implementation settings, so that results can be independently validated. The scope spans AI-for-security (using AI to strengthen cyber defence) and security-of-AI (protecting AI systems from attacks), including privacy, robustness, trust, and responsible use. The journal also welcomes new frameworks, architectures, datasets, benchmarks, tools, and operational approaches that advance secure, reliable, and trustworthy AI-enabled systems.

Topics include, but are not limited to, the following areas:

• Malware detection, classification, reverse engineering
• AI ethics, fairness, accountability, transparency, and governance
• Privacy-preserving AI: federated learning, differential privacy
• Artificial neural networks and Natural language processing 
• Computer/machine vision and multimodal AI
• AI-driven intrusion detection, anomaly detection, 
• AI for phishing, spam detection, fraud detection
• Cyber threat intelligence, automated triage, correlation, 
• Adversarial machine learning: evasion, poisoning, and defences
• Model extraction, data leakage, and inference-time attacks
• Robust and secure model training, validation, and deployment
• Trustworthy and explainable AI for security-critical decision making
• Authentication, identity management, and access control 
• Digital forensics, log analytics, and post-incident investigation 
• Benchmarking, datasets, protocols, and reproducible security