PCA-based membership inference attack for machine learning models
Aiming at the problem of restricted access failure in current black box membership inference attacks, a PCA-based membership inference attack was proposed.Firstly, in order to solve the restricted access problem of black box membership inference attacks, a fast decision membership inference attack n...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2022-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022009/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539942540378112 |
|---|---|
| author | Changgen PENG Ting GAO Huilan LIU Hongfa DING |
| author_facet | Changgen PENG Ting GAO Huilan LIU Hongfa DING |
| author_sort | Changgen PENG |
| collection | DOAJ |
| description | Aiming at the problem of restricted access failure in current black box membership inference attacks, a PCA-based membership inference attack was proposed.Firstly, in order to solve the restricted access problem of black box membership inference attacks, a fast decision membership inference attack named fast-attack was proposed.Based on the perturbation samples obtained by the distance symbol gradient, the perturbation difficulty was mapped to the distance category for membership inference.Secondly, in view of the low mobility problem of fast-attack, a PCA-based membership inference attack was proposed.Combining the algorithmic ideas based on the perturbation category in the fast-attack and the PCA technology to suppress the low-migration behavior caused by excessive reliance on the model.Finally, experiments show that fast-attack reduces the access cost while ensuring the accuracy of the attack.PCA-based attack is superior to the baseline attack under the unsupervised setting, and the migration rate of model is increased by 10% compared to fast-attack. |
| format | Article |
| id | doaj-art-843932a6c76b4290a6542959c6a3a0f0 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2022-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-843932a6c76b4290a6542959c6a3a0f02025-01-14T06:30:30ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2022-01-014314916059398591PCA-based membership inference attack for machine learning modelsChanggen PENGTing GAOHuilan LIUHongfa DINGAiming at the problem of restricted access failure in current black box membership inference attacks, a PCA-based membership inference attack was proposed.Firstly, in order to solve the restricted access problem of black box membership inference attacks, a fast decision membership inference attack named fast-attack was proposed.Based on the perturbation samples obtained by the distance symbol gradient, the perturbation difficulty was mapped to the distance category for membership inference.Secondly, in view of the low mobility problem of fast-attack, a PCA-based membership inference attack was proposed.Combining the algorithmic ideas based on the perturbation category in the fast-attack and the PCA technology to suppress the low-migration behavior caused by excessive reliance on the model.Finally, experiments show that fast-attack reduces the access cost while ensuring the accuracy of the attack.PCA-based attack is superior to the baseline attack under the unsupervised setting, and the migration rate of model is increased by 10% compared to fast-attack.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022009/machine learningadversarial examplemembership inference attackprincipal component analysisprivacy leakage |
| spellingShingle | Changgen PENG Ting GAO Huilan LIU Hongfa DING PCA-based membership inference attack for machine learning models Tongxin xuebao machine learning adversarial example membership inference attack principal component analysis privacy leakage |
| title | PCA-based membership inference attack for machine learning models |
| title_full | PCA-based membership inference attack for machine learning models |
| title_fullStr | PCA-based membership inference attack for machine learning models |
| title_full_unstemmed | PCA-based membership inference attack for machine learning models |
| title_short | PCA-based membership inference attack for machine learning models |
| title_sort | pca based membership inference attack for machine learning models |
| topic | machine learning adversarial example membership inference attack principal component analysis privacy leakage |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2022009/ |
| work_keys_str_mv | AT changgenpeng pcabasedmembershipinferenceattackformachinelearningmodels AT tinggao pcabasedmembershipinferenceattackformachinelearningmodels AT huilanliu pcabasedmembershipinferenceattackformachinelearningmodels AT hongfading pcabasedmembershipinferenceattackformachinelearningmodels |