Improve the robustness of algorithm under adversarial environment by moving target defense
Traditional machine learning models works in peace environment,assuming that training data and test data share the same distribution.However,the hypothesis does not hold in areas like malicious document detection.The enemy attacks the classification algorithm by modifying the test samples so that th...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2020-08-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841529950063034368 |
|---|---|
| author | Kang HE Yuefei ZHU Long LIU Bin LU Bin LIU |
| author_facet | Kang HE Yuefei ZHU Long LIU Bin LU Bin LIU |
| author_sort | Kang HE |
| collection | DOAJ |
| description | Traditional machine learning models works in peace environment,assuming that training data and test data share the same distribution.However,the hypothesis does not hold in areas like malicious document detection.The enemy attacks the classification algorithm by modifying the test samples so that the well-constructed malicious samples can escape the detection by machine learning models.To improve the security of machine learning algorithms,moving target defense (MTD) based method was proposed to enhance the robustness.Experimental results show that the proposed method could effectively resist the evasion attack to detection algorithm by dynamic transformation in the stages of algorithm model,feature selection and result output. |
| format | Article |
| id | doaj-art-2da83fad7b474b4f99e42f2efc52d45e |
| institution | Kabale University |
| issn | 2096-109X |
| language | English |
| publishDate | 2020-08-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 网络与信息安全学报 |
| spelling | doaj-art-2da83fad7b474b4f99e42f2efc52d45e2025-01-15T03:14:15ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2020-08-016677659560123Improve the robustness of algorithm under adversarial environment by moving target defenseKang HEYuefei ZHULong LIUBin LUBin LIUTraditional machine learning models works in peace environment,assuming that training data and test data share the same distribution.However,the hypothesis does not hold in areas like malicious document detection.The enemy attacks the classification algorithm by modifying the test samples so that the well-constructed malicious samples can escape the detection by machine learning models.To improve the security of machine learning algorithms,moving target defense (MTD) based method was proposed to enhance the robustness.Experimental results show that the proposed method could effectively resist the evasion attack to detection algorithm by dynamic transformation in the stages of algorithm model,feature selection and result output.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020052machine learningalgorithm robustnessmoving target defensedynamic transformation |
| spellingShingle | Kang HE Yuefei ZHU Long LIU Bin LU Bin LIU Improve the robustness of algorithm under adversarial environment by moving target defense 网络与信息安全学报 machine learning algorithm robustness moving target defense dynamic transformation |
| title | Improve the robustness of algorithm under adversarial environment by moving target defense |
| title_full | Improve the robustness of algorithm under adversarial environment by moving target defense |
| title_fullStr | Improve the robustness of algorithm under adversarial environment by moving target defense |
| title_full_unstemmed | Improve the robustness of algorithm under adversarial environment by moving target defense |
| title_short | Improve the robustness of algorithm under adversarial environment by moving target defense |
| title_sort | improve the robustness of algorithm under adversarial environment by moving target defense |
| topic | machine learning algorithm robustness moving target defense dynamic transformation |
| url | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2020052 |
| work_keys_str_mv | AT kanghe improvetherobustnessofalgorithmunderadversarialenvironmentbymovingtargetdefense AT yuefeizhu improvetherobustnessofalgorithmunderadversarialenvironmentbymovingtargetdefense AT longliu improvetherobustnessofalgorithmunderadversarialenvironmentbymovingtargetdefense AT binlu improvetherobustnessofalgorithmunderadversarialenvironmentbymovingtargetdefense AT binliu improvetherobustnessofalgorithmunderadversarialenvironmentbymovingtargetdefense |