A Learning-Based Hierarchical Edge Data Corruption Detection Framework in Edge Intelligence

Edge intelligence, an emerging distributed paradigm, is driven by the increasing number of Internet of Things devices and the development of edge computing and artificial intelligence. This paradigm revolutionizes the way of data caching by encouraging latency-sensitive data to be distributed across multiple edge nodes. In such data caching scenarios, ensuring the integrity of data stored at the edge nodes is critical for business continuity guarantee. Existing Edge Data Integrity (EDI) verification solutions rely on the interactive Challenge-Response mechanism. However, this mechanism imposes significant communication overhead on participants, leading to low verification efficiency. To address this challenge, we propose a Learning-based Hierarchical Edge Data Corruption Detection framework (LH-EDCD), aiming to enhance verification efficiency from a round perspective by reducing communication interaction between edge nodes and the data owner. LH-EDCD involves two layers of verification: internal and external. In the internal verification layer, each edge node self-inspects the cached data replica by running a corruption detection model distributedly trained by blockchain-based Federated Learning (FL). With such filtration, potential corruption can be efficiently identified without complex interaction. Considering the false positive existence in the model, in the external verification layer, LH-EDCD adopts a smart contract in blockchain to verify identified potentially corrupted data replicas for corruption confirmation, mitigating the trust concerns among edge nodes while reducing communication overhead on backbone networks. With the combination of these two layers, the overall EDI verification efficiency can be improved by reducing interaction verification time. Additionally, we make the first attempt to investigate the optimal verification time to improve the applicability and practicality of LH-EDCD. Extensive experimental results substantiate the advantages of employing FL in the first layer of LH-EDCD and demonstrate that LH-EDCD outperforms two state-of-the-art EDI approaches, i.e., EDI-S and EDI-V. Specifically, LH-EDCD achieves better model accuracy and convergence speed compared to centralized training, while exhibiting superior efficiency over EDI-S and EDI-V with 3.5 and 2.8 times performance improvements, respectively.