Privacy-Preserving Task Offloading Scheme Based on Blockchain Federated Learning in End-Edge-Cloud Computing Environments

With the continuous advancement of the Internet of Things (IoT) and mobile terminal technologies, the massive data generated by end devices poses new challenges for real-time processing in cloud computing. As a beneficial complement to cloud computing, edge computing has garnered significant attention due to its ability to provide low-latency services near the data source. However, user privacy data involved in the task offloading process faces leakage risks in open edge architectures, and existing solutions still lack synergy between privacy protection and computational efficiency. To address this, this paper proposes a privacy-preserving task offloading scheme for end-edge-cloud architectures based on blockchain federated learning. The main contributions are as follows: (1) constructing a collaborative computing architecture that integrates end devices, edge servers, and cloud centers; (2) proposing a privacy-preserving task offloading mechanism that integrates federated learning and blockchain technology, enabling distributed model training and secure auditing without sharing raw data; (3) validating the superiority of the proposed scheme in terms of energy consumption, latency, and privacy protection level through simulation experiments. The experimental results demonstrate that the proposed scheme significantly enhances user privacy protection while maintaining efficient task processing, providing a reliable technical approach for privacy-sensitive applications in edge computing environments.