The Journal of Trustworthy and Explainable Intelligent Systems is an international, peer-reviewed, open access journal published by Transparent Intelligence Publishing. The journal advances research on the design, analysis, evaluation, and deployment of intelligent systems that are trustworthy, explainable, safe, reliable, secure, fair, and accountable. It welcomes work that develops technical foundations and practical methods for understanding intelligent-system behavior and for establishing justified confidence in AI-assisted decisions and autonomous operation.
The journal covers both intrinsic and post-hoc explainability together with complementary dimensions of trustworthiness, including robustness, reliability, uncertainty, safety, security, privacy, fairness, accountability, verification, and human oversight. Particular attention is given to methods that connect technical evidence with human understanding, support risk-aware decision-making, and enable the responsible deployment and governance of intelligent systems in real-world environments.
The journal welcomes original research articles, review articles, systematic review articles, and case studies on trustworthy and explainable intelligent systems. Relevant contributions may address theoretical foundations, algorithms, system architectures, evaluation frameworks, assurance and validation methods, practical implementations, standards, and interdisciplinary research connecting artificial intelligence with human-computer interaction, cybersecurity, robotics, cognitive science, ethics, law, and regulatory compliance.
The scope of the journal includes, but is not limited to:
Interpretable-by-design AI, transparent models, and explainable intelligent-system architectures
Post-hoc explanation, feature attribution, concept-based explanations, and saliency methods
Explainable artificial intelligence (XAI), model-agnostic explanation, and explanation generation
Interpretability of deep learning, foundation models, generative AI, and large language models
Causal AI, causal discovery, counterfactual reasoning, and actionable explanations
Trustworthy and responsible AI, including robustness, reliability, fairness, accountability, and transparency
Human-AI interaction, human-centered explainability, calibrated trust, and explanation interfaces
Uncertainty quantification, calibration, confidence estimation, and risk-aware prediction
Metrics, benchmarks, and evaluation protocols for trustworthiness, explanation quality, faithfulness, and stability
Explainable natural language processing, conversational AI, and natural-language explanations
Explainable computer vision, multimodal AI, and interpretable perception systems
Trustworthy and explainable AI applications in healthcare, finance, cybersecurity, critical infrastructure, autonomous systems, and other high-stakes domains
AI governance, standards, auditing, regulatory compliance, ethics, and societal aspects of trustworthy intelligent systems
Knowledge-driven, neuro-symbolic, and hybrid approaches to explainability and assurance
Model and system auditing, red-teaming, debugging, verification, validation, and assurance tools
Cognitive and psychological foundations of explanation, trust, reliance, and human understanding of AI
We particularly encourage interdisciplinary research that combines artificial intelligence with human-computer interaction, cybersecurity, robotics, cognitive science, ethics, law, and regulatory studies to address challenges in explainability, safety, security, accountability, fairness, and trustworthy decision-making.
Purely theoretical computer science or engineering studies without a clear contribution to the trustworthiness, explainability, assurance, evaluation, or responsible use of intelligent systems are outside the scope of the journal.
Transparent Intelligence Publishing