Intelligent Privacy: Preserving Split Learning Framework for Decentralisation Data Deduplication in Edge Environment

Abstract

: Driven by the emergence of edge computing and its ever-growing need for more efficient systems to manage information of ever-increasing volume, privacy-preserving digital fingerprint and distributed learning have received far greater importance in recent years decade contributions from this author When by advertising ``split '', a novel technique has emerged that retains data deduplication and decentralization, but also solves issues such as privacy resource usage and scalability. Different from current literature that largely sacrifices de-duplication accuracy or improved copy finding as a result of focusing exclusively on either the problem of de-duplication, machine learning, ours approach in developing high-slash, splits with splits come together to do intelligent data management and a reasonable measure of privacy.This paper uses the existing methods of fine-grained deduplication, resource allocation, and blockchain-based decentralized system to extend this idea, providing a safe and efficient solution for edge computing. Dependencies testing implies that the adaptability and efficiency of the framework are validated by experimental simulations, and the results have demonstrated its effectiveness in eliminating redundant data, as well as improving the performance of edge-located machine learning systems.