Privacy-Preserving Federated Learning With Meta-Knowledge Training for AIoT-Enabled Supply Chain Systems: A Case Study on Smart Healthcare

Artificial Intelligence-of-Things (AIoT)-enabled supply chain systems (SCS) face critical challenges in balancing operational efficiency with privacy preservation. While federated learning (FL) offers a decentralized solution for collaborative model training without raw data sharing, it still remains vulnerable to adversarial attacks, such as gradient inversion and poisoning attacks, which would raise the risk of privacy leakage in SCS. This paper proposes a novel privacy-preserving FL framework that leverages meta-knowledge training to address these limitations. The proposed framework introduces two key innovations. First, a meta-knowledge extraction mechanism is designed to extract meta-knowledge from the training neural networks. Second, a meta-knowledge-based FL method that exchanges only meta-knowledge instead of full gradients is proposed. Since meta-knowledge is just condensed information from the whole network, exchanging it preserves privacy. Finally, we conduct experiments for smart healthcare applications. The experimental results justify that the proposed framework obtains better performance and convergence. Overall, the proposed framework could enable secure AIoT deployments for SCS, offering a scalable solution for real-world applications.