Blockchain based Trusted Execution Environment Architecture Analysis for Multi - source Data Fusion Scenario

Abstract

Multi-source data fusion techniques are widely applied in dynamic target detection scenarios, such as target situational awareness, radar signal resolution, and feature fusion labeling. Currently, techniques including clustering, neural networks, Bayesian analysis, and machine learning have been applied to improve the success rate of multi-source data fusion in terms of interference data noise reduction. However, there are fewer studies and applications in terms of data tamper-proofing from the data source itself and running the computation process in a trusted execution environment. Accordingly, this paper proposes a trusted execution environment architecture based on blockchain technology for multi-source data fusion scenarios, and integrates the strategy of trusted data source data verification in blockchain smart contracts into the typical multi-source data fusion application architecture. After comparison tests in a simulation environment, the trusted execution environment architecture based on blockchain technology is able to obtain a considerable improvement in fusion success rate with limited performance cost.