Research on Automated Detection of Sensitive Information Based on BERT

Meng Ding; Xing Wang; Changming Wu; Kaixuan Wang; Xue Yang

doi:10.1088/1742-6596/1757/1/012088

Research on Automated Detection of Sensitive Information Based on BERT

Meng Ding^*
, Xing Wang
, Changming Wu
, Kaixuan Wang
, Xue Yang

^*Corresponding author for this work

Chinese People's Public Security University

Research output: Contribution to journal › Conference article › peer-review

11 Scopus citations

Abstract

With the booming of the Internet, Web public opinion plays an increasingly important role in the stability of the network community. Therefore, the sensitive information hidden on the Internet is likely to lead to unpredictable social impact. This paper focuses on the detection of Chinese sensitive information. First, we build a corpus to train the detection model. Secondly, we apply the Bert method to the detection problem. Then, many popular NLP methods are applied to this problem to show the progress of Bert in a sensitive information detection task. Finally, we got a sensitive information detection model based on BERT with a high F1 score of 97.31.

Original language	English
Article number	012088
Journal	Journal of Physics: Conference Series
Volume	1757
Issue number	1
DOIs	https://doi.org/10.1088/1742-6596/1757/1/012088
State	Published - 3 Feb 2021
Externally published	Yes
Event	2020 International Conference on Computer Big Data and Artificial Intelligence, ICCBDAI 2020 - Changsha, China Duration: 24 Oct 2020 → 25 Oct 2020

Keywords

component
formatting
style
styling

Access to Document

10.1088/1742-6596/1757/1/012088

Cite this

@article{8329b3d8b4454998a2d9f0626a3a5afe,

title = "Research on Automated Detection of Sensitive Information Based on BERT",

abstract = "With the booming of the Internet, Web public opinion plays an increasingly important role in the stability of the network community. Therefore, the sensitive information hidden on the Internet is likely to lead to unpredictable social impact. This paper focuses on the detection of Chinese sensitive information. First, we build a corpus to train the detection model. Secondly, we apply the Bert method to the detection problem. Then, many popular NLP methods are applied to this problem to show the progress of Bert in a sensitive information detection task. Finally, we got a sensitive information detection model based on BERT with a high F1 score of 97.31.",

keywords = "component, formatting, style, styling",

author = "Meng Ding and Xing Wang and Changming Wu and Kaixuan Wang and Xue Yang",

note = "Publisher Copyright: {\textcopyright} Published under licence by IOP Publishing Ltd.; 2020 International Conference on Computer Big Data and Artificial Intelligence, ICCBDAI 2020 ; Conference date: 24-10-2020 Through 25-10-2020",

year = "2021",

month = feb,

day = "3",

doi = "10.1088/1742-6596/1757/1/012088",

language = "英语",

volume = "1757",

journal = "Journal of Physics: Conference Series",

issn = "1742-6588",

publisher = "IOP Publishing Ltd.",

number = "1",

}

TY - JOUR

T1 - Research on Automated Detection of Sensitive Information Based on BERT

AU - Ding, Meng

AU - Wang, Xing

AU - Wu, Changming

AU - Wang, Kaixuan

AU - Yang, Xue

N1 - Publisher Copyright: © Published under licence by IOP Publishing Ltd.

PY - 2021/2/3

Y1 - 2021/2/3

N2 - With the booming of the Internet, Web public opinion plays an increasingly important role in the stability of the network community. Therefore, the sensitive information hidden on the Internet is likely to lead to unpredictable social impact. This paper focuses on the detection of Chinese sensitive information. First, we build a corpus to train the detection model. Secondly, we apply the Bert method to the detection problem. Then, many popular NLP methods are applied to this problem to show the progress of Bert in a sensitive information detection task. Finally, we got a sensitive information detection model based on BERT with a high F1 score of 97.31.

AB - With the booming of the Internet, Web public opinion plays an increasingly important role in the stability of the network community. Therefore, the sensitive information hidden on the Internet is likely to lead to unpredictable social impact. This paper focuses on the detection of Chinese sensitive information. First, we build a corpus to train the detection model. Secondly, we apply the Bert method to the detection problem. Then, many popular NLP methods are applied to this problem to show the progress of Bert in a sensitive information detection task. Finally, we got a sensitive information detection model based on BERT with a high F1 score of 97.31.

KW - component

KW - formatting

KW - style

KW - styling

UR - https://www.scopus.com/pages/publications/85102404649

U2 - 10.1088/1742-6596/1757/1/012088

DO - 10.1088/1742-6596/1757/1/012088

M3 - 会议文章

AN - SCOPUS:85102404649

SN - 1742-6588

VL - 1757

JO - Journal of Physics: Conference Series

JF - Journal of Physics: Conference Series

IS - 1

M1 - 012088

T2 - 2020 International Conference on Computer Big Data and Artificial Intelligence, ICCBDAI 2020

Y2 - 24 October 2020 through 25 October 2020

ER -

Research on Automated Detection of Sensitive Information Based on BERT

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this