The Internet of Things (IoT) is becoming smarter and more capable empowered by recent advances in Artificial Intelligence (AI). As the deployment of IoT products grows rapidly in our cyber infrastructure, threats targeting IoT ecosystems are increasing at an alarming rate. Consequently, supporting and optimizing IoT security to increase the resilience of our critical cyber infrastructure is essential. Traditional methodologies cannot effectively scale up to the capability and efficacy required to keep up with today's ever-escalating cybersecurity threats. Thus, it is urgently necessary to design and develop novel approaches, algorithms, and technologies for securing AI-based IoT ecosystems.

AI can cause significant disruptions in IoT ecosystems whether it is a failure of the AI engine or because a malicious actor is causing it to behave in unexpected ways. Therefore, it is important to improve the security of the underlining AI algorithms and applications, and to detect improper AI usage in IoT systems.

The aim of this Special Issue is to collate original research and review articles with a focus on interpretable AI, AI application fault/risk detection and prevention, AI ethical privacy and AI safety amongst other topics.

Potential topics include but are not limited to the following:

• Interpretable and transparent AI in IoT
• Secured and privacy preserved IoT applications
• AI based security/privacy issue detection in IoT
• AI based privacy protection in IoT
• AI based security enhancement in IoT
• Federated learning in IoT
• Incentive mechanism design for collaborative training in IoT
• Novel collaborative training platform design in IoT
• Secure collaborative training application design in IoT
• Fairness control in collaborative training