Deep Learning Based Fusion Models for Sensitive Information Identification

Abstract

The rapid expansion of information on the Internet and mobile Internet has led to the proliferation of sensitive information, which affects the harmony of the Internet. However, the traditional text sensitive information identification method based on sensitive words matching have the problems of ignoring context semantics, resulting in high false positive rate and low accuracy. This paper proposes a sensitive information identification fusion model combining sensitive words matching and deep learning. This novel fusion model can effectively solve the problem of high false positive rate caused by the lack of semantic understanding in traditional identification method, thus improving the accuracy and efficiency of sensitive information identification. This paper also proposes a sensitive information identification system using the fusion model and carries out experimental verification.