Privacy protection risk identification mechanism based on automated feature combination
In practice, the anomaly detection (AD) algorithm usually faced technical challenges such as difficulty in optimizing feature combinations, difficulty in improving classifier accuracy, and low model application efficiency. The multidimensional data generated by users was with rich spatial structure...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2024-11-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024194/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537114980745216 |
|---|---|
| author | CAI Minchao YAO Hongwei WANG Yang QIN Zhan CHEN Shaomeng REN Kui |
| author_facet | CAI Minchao YAO Hongwei WANG Yang QIN Zhan CHEN Shaomeng REN Kui |
| author_sort | CAI Minchao |
| collection | DOAJ |
| description | In practice, the anomaly detection (AD) algorithm usually faced technical challenges such as difficulty in optimizing feature combinations, difficulty in improving classifier accuracy, and low model application efficiency. The multidimensional data generated by users was with rich spatial structure information, revolved around the characteristics of the multidimensional data. Building upon the privacy protection method using homomorphic encryption, the technical challenge of optimizing feature combinations was addressed. The first automated feature combination optimization model algorithm based on feature binning was proposed and implemented. This algorithm enhanced computational efficiency in feature combination optimization by 99.93%. The rules combined by the important features selected by the automatic feature combination optimization model still faced the technical challenge of difficulty in improving the classifier accuracy. Therefore, the important features selected automatically were integrated into the recognition model, the first cross-application model of rules and algorithms was designed and implemented. This approach was applied to anomaly detection based on multi-dimensional user data, resulting in a 27.78% increase in funds saved in the specific scenario of identifying abnormal users who enjoy first but do not pay. |
| format | Article |
| id | doaj-art-40240d914f8b4909abf1922323eddaac |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2024-11-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-40240d914f8b4909abf1922323eddaac2025-01-14T08:46:21ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2024-11-014511479134512Privacy protection risk identification mechanism based on automated feature combinationCAI MinchaoYAO HongweiWANG YangQIN ZhanCHEN ShaomengREN KuiIn practice, the anomaly detection (AD) algorithm usually faced technical challenges such as difficulty in optimizing feature combinations, difficulty in improving classifier accuracy, and low model application efficiency. The multidimensional data generated by users was with rich spatial structure information, revolved around the characteristics of the multidimensional data. Building upon the privacy protection method using homomorphic encryption, the technical challenge of optimizing feature combinations was addressed. The first automated feature combination optimization model algorithm based on feature binning was proposed and implemented. This algorithm enhanced computational efficiency in feature combination optimization by 99.93%. The rules combined by the important features selected by the automatic feature combination optimization model still faced the technical challenge of difficulty in improving the classifier accuracy. Therefore, the important features selected automatically were integrated into the recognition model, the first cross-application model of rules and algorithms was designed and implemented. This approach was applied to anomaly detection based on multi-dimensional user data, resulting in a 27.78% increase in funds saved in the specific scenario of identifying abnormal users who enjoy first but do not pay.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024194/anomaly detectionmulti-dimensional informationrisk identificationtrustworthiness modelhomomorphic encryption |
| spellingShingle | CAI Minchao YAO Hongwei WANG Yang QIN Zhan CHEN Shaomeng REN Kui Privacy protection risk identification mechanism based on automated feature combination Tongxin xuebao anomaly detection multi-dimensional information risk identification trustworthiness model homomorphic encryption |
| title | Privacy protection risk identification mechanism based on automated feature combination |
| title_full | Privacy protection risk identification mechanism based on automated feature combination |
| title_fullStr | Privacy protection risk identification mechanism based on automated feature combination |
| title_full_unstemmed | Privacy protection risk identification mechanism based on automated feature combination |
| title_short | Privacy protection risk identification mechanism based on automated feature combination |
| title_sort | privacy protection risk identification mechanism based on automated feature combination |
| topic | anomaly detection multi-dimensional information risk identification trustworthiness model homomorphic encryption |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2024194/ |
| work_keys_str_mv | AT caiminchao privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination AT yaohongwei privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination AT wangyang privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination AT qinzhan privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination AT chenshaomeng privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination AT renkui privacyprotectionriskidentificationmechanismbasedonautomatedfeaturecombination |