Securing the 6G-IoT Environment: A Framework for Enhancing Transparency in Artificial Intelligence Decision-Making Through Explainable Artificial Intelligence.

Wireless communication advancements have significantly improved connectivity and user experience with each generation. The recent release of the framework M.2160 for the upcoming sixth generation (6G or IMT-2030) cellular wireless standard by ITU-R has significantly heightened expectations, particularly for Internet of Things (IoT) driven use cases. However, this progress introduces significant security risks, as technologies like O-RAN, terahertz communication, and native AI pose threats such as eavesdropping, supply chain vulnerabilities, model poisoning, and adversarial attacks. The increased exposure of sensitive data in 6G applications further intensifies these challenges. This necessitates a concerted effort from stakeholders including ITU-R, 3GPP, ETSI, OEMs and researchers to embed security and resilience as core components of 6G. While research is advancing, establishing a comprehensive security framework remains a significant challenge. To address these evolving threats, our research proposes a dynamic security framework that emphasizes the integration of explainable AI (XAI) techniques like SHAP and LIME with advanced machine learning models to enhance decision-making transparency, improve security in complex 6G environments, and ensure effective detection and mitigation of emerging cyber threats. By refining model accuracy and ensuring alignment through recursive feature elimination and consistent cross-validation, our approach strengthens the overall security posture of the IoT-6G ecosystem, making it more resilient to adversarial attacks and other vulnerabilities.