Adversarial sample generation algorithm for vertical federated learning
To adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample ge...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-08-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023149/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540039429849088 |
|---|---|
| author | Xiaolin CHEN Daoguang ZAN Bingchao WU Bei GUAN Yongji WANG |
| author_facet | Xiaolin CHEN Daoguang ZAN Bingchao WU Bei GUAN Yongji WANG |
| author_sort | Xiaolin CHEN |
| collection | DOAJ |
| description | To adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample generation framework was constructed for the VFL architecture.A white-box adversarial attack in the VFL was implemented by extending the centralized machine learning adversarial sample generation algorithm with different policies such as L-BFGS, FGSM, and C＆amp;W.By introducing deep convolutional generative adversarial network (DCGAN), an adversarial sample generation algorithm named VFL-GASG was designed to address the problem of universality in the generation of adversarial perturbations.Hidden layer vectors were utilized as local prior knowledge to train the adversarial perturbation generation model, and through a series of convolution-deconvolution network layers, finely crafted adversarial perturbations were produced.Experiments show that VFL-GASG can maintain a high attack success while achieving a higher generation efficiency, robustness, and generalization ability than the baseline algorithm, and further verify the impact of relevant settings for adversarial attacks. |
| format | Article |
| id | doaj-art-4dd80e2d1f5b4039ab5c3369129c104e |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-08-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-4dd80e2d1f5b4039ab5c3369129c104e2025-01-14T06:22:43ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-08-014411359385638Adversarial sample generation algorithm for vertical federated learningXiaolin CHENDaoguang ZANBingchao WUBei GUANYongji WANGTo adapt to the scenario characteristics of vertical federated learning (VFL) applications regarding high communication cost, fast model iteration, and decentralized data storage, a generalized adversarial sample generation algorithm named VFL-GASG was proposed.Specifically, an adversarial sample generation framework was constructed for the VFL architecture.A white-box adversarial attack in the VFL was implemented by extending the centralized machine learning adversarial sample generation algorithm with different policies such as L-BFGS, FGSM, and C＆amp;W.By introducing deep convolutional generative adversarial network (DCGAN), an adversarial sample generation algorithm named VFL-GASG was designed to address the problem of universality in the generation of adversarial perturbations.Hidden layer vectors were utilized as local prior knowledge to train the adversarial perturbation generation model, and through a series of convolution-deconvolution network layers, finely crafted adversarial perturbations were produced.Experiments show that VFL-GASG can maintain a high attack success while achieving a higher generation efficiency, robustness, and generalization ability than the baseline algorithm, and further verify the impact of relevant settings for adversarial attacks.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023149/machine learningVFLadversarial sampleadversarial attackDCGAN |
| spellingShingle | Xiaolin CHEN Daoguang ZAN Bingchao WU Bei GUAN Yongji WANG Adversarial sample generation algorithm for vertical federated learning Tongxin xuebao machine learning VFL adversarial sample adversarial attack DCGAN |
| title | Adversarial sample generation algorithm for vertical federated learning |
| title_full | Adversarial sample generation algorithm for vertical federated learning |
| title_fullStr | Adversarial sample generation algorithm for vertical federated learning |
| title_full_unstemmed | Adversarial sample generation algorithm for vertical federated learning |
| title_short | Adversarial sample generation algorithm for vertical federated learning |
| title_sort | adversarial sample generation algorithm for vertical federated learning |
| topic | machine learning VFL adversarial sample adversarial attack DCGAN |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023149/ |
| work_keys_str_mv | AT xiaolinchen adversarialsamplegenerationalgorithmforverticalfederatedlearning AT daoguangzan adversarialsamplegenerationalgorithmforverticalfederatedlearning AT bingchaowu adversarialsamplegenerationalgorithmforverticalfederatedlearning AT beiguan adversarialsamplegenerationalgorithmforverticalfederatedlearning AT yongjiwang adversarialsamplegenerationalgorithmforverticalfederatedlearning |