Dual-branch autoencoder network for attacking deep hashing image retrieval models
Due to its powerful representation learning capabilities and efficient computing capabilities, deep learning-based hashing (deep hashing) methods are widely used in large-scale image retrieval.However, there are less studies on the security of deep hashing models.A dual-branch autoencoder network (D...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2023-11-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023246/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533647243444224 |
|---|---|
| author | Sizheng FU Chunjie CAO Zhiyuan LIU Fangjian TAO Jingzhang SUN |
| author_facet | Sizheng FU Chunjie CAO Zhiyuan LIU Fangjian TAO Jingzhang SUN |
| author_sort | Sizheng FU |
| collection | DOAJ |
| description | Due to its powerful representation learning capabilities and efficient computing capabilities, deep learning-based hashing (deep hashing) methods are widely used in large-scale image retrieval.However, there are less studies on the security of deep hashing models.A dual-branch autoencoder network (DBAE) to study targeted attacks on such retrieval was proposed.The main goal of DBAE was to generate imperceptible adversarial samples as query images in order to make the images retrieved by the deep hashing model semantically irrelevant to the original image and relevant to the target image.Numerous experiments demonstrate that DBAE can successfully generate adversarial samples with small perturbations to mislead deep hashing models, and italso verifies the transferability of these perturbations under various settings. |
| format | Article |
| id | doaj-art-83431b98bb5b4655862c9871d5871731 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2023-11-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-83431b98bb5b4655862c9871d58717312025-01-15T02:57:56ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012023-11-01399610659559357Dual-branch autoencoder network for attacking deep hashing image retrieval modelsSizheng FUChunjie CAOZhiyuan LIUFangjian TAOJingzhang SUNDue to its powerful representation learning capabilities and efficient computing capabilities, deep learning-based hashing (deep hashing) methods are widely used in large-scale image retrieval.However, there are less studies on the security of deep hashing models.A dual-branch autoencoder network (DBAE) to study targeted attacks on such retrieval was proposed.The main goal of DBAE was to generate imperceptible adversarial samples as query images in order to make the images retrieved by the deep hashing model semantically irrelevant to the original image and relevant to the target image.Numerous experiments demonstrate that DBAE can successfully generate adversarial samples with small perturbations to mislead deep hashing models, and italso verifies the transferability of these perturbations under various settings.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023246/targeted attackdeep hashingadversarial attackimage retrieval |
| spellingShingle | Sizheng FU Chunjie CAO Zhiyuan LIU Fangjian TAO Jingzhang SUN Dual-branch autoencoder network for attacking deep hashing image retrieval models Dianxin kexue targeted attack deep hashing adversarial attack image retrieval |
| title | Dual-branch autoencoder network for attacking deep hashing image retrieval models |
| title_full | Dual-branch autoencoder network for attacking deep hashing image retrieval models |
| title_fullStr | Dual-branch autoencoder network for attacking deep hashing image retrieval models |
| title_full_unstemmed | Dual-branch autoencoder network for attacking deep hashing image retrieval models |
| title_short | Dual-branch autoencoder network for attacking deep hashing image retrieval models |
| title_sort | dual branch autoencoder network for attacking deep hashing image retrieval models |
| topic | targeted attack deep hashing adversarial attack image retrieval |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2023246/ |
| work_keys_str_mv | AT sizhengfu dualbranchautoencodernetworkforattackingdeephashingimageretrievalmodels AT chunjiecao dualbranchautoencodernetworkforattackingdeephashingimageretrievalmodels AT zhiyuanliu dualbranchautoencodernetworkforattackingdeephashingimageretrievalmodels AT fangjiantao dualbranchautoencodernetworkforattackingdeephashingimageretrievalmodels AT jingzhangsun dualbranchautoencodernetworkforattackingdeephashingimageretrievalmodels |