With the rapid growth in the sophistication and impact of artificial intelligence (AI) tools, particularly largescale AI models, AI have begun to reshape daily life and a wide range of critical domains, including defense, manufacturing, transportation, and health sciences. However, realizing the full potential of AI requires that its outcomes be trustworthy and deserving of human confidence. To address this challenge, trustworthy AI seeks to align AI systems with human values, including accountability, reliability, transparency, robustness, and fairness. By embedding these principles into the design, deployment, and evaluation of AI systems, trustworthy AI aims to ensure safe, ethical, and dependable AI technologies.

Topic of Interests:
This special issue of the IEEE Trans. Reliability aims to bring together high-quality, original research on AI Safety and Trustworthy AI. We invite submissions on topics including, but not limited to, the following:

• AI for reliability assessment and prognostics • Fairness and bias mitigation

• Transparency and auditability

• Robust and fault-tolerant AI/ML algorithms

• Verification, validation, and assurance of AI models

• Privacy preserving techniques such as federated learning

• Standards and metrics for AI system reliability

• Data sets for trustworthy AI research

• Regulation and governance

• Explainable AI (XAI) for critical decision-making

• Secure, adversary-resilient, and self-recoverable AI systems

• Human-AI interaction and teaming

• Information reliability

Submission Guidelines

All submissions will undergo the IEEE Transaction on Reliability’s rigorous peer-review process. Authors should submit their manuscripts through https://mc.manuscriptcentral.com/tr-ieee IEEE Transaction on Reliability’s submission portal, selecting the article type “TRel-TR: Special Session on Trustworthy and Reliable AI” to ensure consideration for this special issue. Authors should also reference this special issue in their cover letters.

Guest Editors

• Henry Leung, University of Calgary, Canada; Email: leungh@ucalgary.ca

• Ruonan Liu, Shanghai Jiao Tong University, China; Email: ruonan.liu@sjtu.edu.cn

• Angelos Stavrou, Virginia Tech, USA; Email: angelos@vt.edu

• Ruolin Zhou, University of Massachusetts Dartmouth, USA; Email: rzhou1@umassd.edu

Important Dates

• Manuscript Submission Deadline: June 30, 2026

• First Review Decision: Sept 30, 2026

• Revised Manuscript Submission: Oct 31, 2026

• Final Decision Notification: Dec 31, 2026