Research Article
A Machine Learning Based Security Detection Method for Privacy Data in Social Networks
@INPROCEEDINGS{10.1007/978-3-031-50543-0_24, author={Zhiyu Huang and Chenyang Li}, title={A Machine Learning Based Security Detection Method for Privacy Data in Social Networks}, proceedings={Advanced Hybrid Information Processing. 7th EAI International Conference, ADHIP 2023, Harbin, China, September 22-24, 2023, Proceedings, Part I}, proceedings_a={ADHIP}, year={2024}, month={3}, keywords={N-Gram language model Semantic vector Deviation coefficient machine learning}, doi={10.1007/978-3-031-50543-0_24} }- Zhiyu Huang
Chenyang Li
Year: 2024
A Machine Learning Based Security Detection Method for Privacy Data in Social Networks
ADHIP
Springer
DOI: 10.1007/978-3-031-50543-0_24
Abstract
In order to improve the social Internet privacy data security detection effect and improve the data security detection efficiency, this paper proposes a social Internet privacy data security detection method based on machine learning. First, collect social Internet privacy data and construct N-Gram language model to realize the standardization of social Internet privacy data; Secondly, a semantic vector based representation model is used to obtain topic semantic vectors, and the obtained topic semantic vectors are matched; Finally, social Internet privacy data security risk detection is carried out by using the skew coefficient method in machine learning. The results show that the method in this paper effectively compresses the time consumption of security detection through machine learning. The time consumption of detection is only 5.3 s, and the accuracy of data detection can reach 99.5%. The method in this paper can effectively improve the efficiency of social Internet privacy data security detection and improve the detection accuracy, but the detection cost needs to be reduced.
