Machine Learning in the Application of Fraudulent SMS Filtering

Yihe Huang

doi:10.62051/ijcsit.v4n3.34

Authors

Yihe Huang

DOI:

https://doi.org/10.62051/ijcsit.v4n3.34

Keywords:

Electronic fraud SMS filtering, Feature selection, HHO-KNN algorithm, Intuitive fuzzy set

Abstract

Electronic fraud SMS is a common network security threat, which brings huge economic and privacy risks to users. To effectively address this problem, this paper studies the electronic scam SMS filtering method based on machine learning. By analyzing and processing a large number of SMS datasets, we propose a classification model that comprehensively considers both textual and behavioral features to identify and filter e-scam text messages. The experimental results show that our method achieves significant improvements in accuracy and efficiency and provides better security for users.

Downloads

Download data is not yet available.

References

[1] Research on spam detection based on HHO-KNN optimization algorithm_Chen Liang.pdf

[2] Aljarah, I., Faris, H., & Mirjalili, S. (2019). Hybrid krill herd algorithm with k-nearest neighbors for data classification. Applied Soft Computing, 74, 166-175.

[3] Aljarah, I., Faris, H., & Mirjalili, S. (2018). Optimizing the training parameters of support vector machines using hybrid harmony search algorithm. Neural Computing and Applications, 29(11), 1073-1086.

[4] Aljarah, I., Faris, H., & Mirjalili, S. (2017). HHO-KNN: A hybrid harmony search algorithm with k-nearest neighbors for data classification. Expert Systems with Applications, 77, 236-250.

[5] Li, X., Zhang, Y., & Zhang, J. (2019). Feature selection for spam detection using a hybrid KNN-HHO algorithm. Journal of Computational Science, 31, 140-148.

[6] Wang, X., & Li, X. (2018). A novel hybrid KNN-HHO algorithm for feature selection. PloS one, 13(5), e0197396.

[7] Liu Cheng, Chen Xi, Wu Wenbo. Research on spam SMS analysis and management technology [J]. Guangdong Communication Technology, 2022, 42 (06): 16-20.

[8] Li Shu. Escape attack and its application in Chinese spam message filtering [D]. Nanjing University of Posts and Telecommunications, 2018.

[9] Zhang Yan, Liu Yin, Liu Shengping, etc. Research on intelligent governance system for spam SMS [J]. Telecommunications Network Technology, 2017, No.282(12):67-71.

[10] Xia, Tian, and Xuemin Chen."A Discrete Hidden Markov Model for SMS Spam Detection." Applied Sciences (2020).