基于图像小波域自适应干扰的GAN生成人脸反取证
TP391.4; 针对现有生成对抗网络(GAN)生成人脸反取证方法攻击迁移性不强的问题,提出了一个基于图像小波域自适应干扰的GAN生成人脸反取证方法以提升攻击迁移性.该方法通过对GAN生成人脸图像的小波域信息(即图像经过小波分解后的频率分量)施加扰动以实现其对取证模型的抵抗,并且分别在空域和频域上基于最小可觉察误差(JND)设计自适应扰动阈值,对图像不同像素点位置设置不同的扰动强度,从而增强扰动的人眼不可感知性.此外,还设计了一种数据增强方式对反取证人脸进行数据分布多样性扩充,以进一步提升攻击迁移性.实验结果表明,与6种基线方法相比,所提方法生成的反取证人脸在保证扰动对人眼不可感知前提下具有更...
Saved in:
| Published in | 东南大学学报（自然科学版） Vol. 54; no. 5; pp. 1330 - 1338 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
南京信息工程大学计算机学院,南京 210044
01.09.2024
南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京 210044%南京信息工程大学计算机学院,南京 210044%东南大学影像科学与技术实验室,南京 210096 |
| Subjects | |
| Online Access | Get full text |
| ISSN | 1001-0505 |
| DOI | 10.3969/j.issn.1001-0505.2024.05.030 |
Cover
| Abstract | TP391.4; 针对现有生成对抗网络(GAN)生成人脸反取证方法攻击迁移性不强的问题,提出了一个基于图像小波域自适应干扰的GAN生成人脸反取证方法以提升攻击迁移性.该方法通过对GAN生成人脸图像的小波域信息(即图像经过小波分解后的频率分量)施加扰动以实现其对取证模型的抵抗,并且分别在空域和频域上基于最小可觉察误差(JND)设计自适应扰动阈值,对图像不同像素点位置设置不同的扰动强度,从而增强扰动的人眼不可感知性.此外,还设计了一种数据增强方式对反取证人脸进行数据分布多样性扩充,以进一步提升攻击迁移性.实验结果表明,与6种基线方法相比,所提方法生成的反取证人脸在保证扰动对人眼不可感知前提下具有更强的攻击迁移性. |
|---|---|
| AbstractList | TP391.4; 针对现有生成对抗网络(GAN)生成人脸反取证方法攻击迁移性不强的问题,提出了一个基于图像小波域自适应干扰的GAN生成人脸反取证方法以提升攻击迁移性.该方法通过对GAN生成人脸图像的小波域信息(即图像经过小波分解后的频率分量)施加扰动以实现其对取证模型的抵抗,并且分别在空域和频域上基于最小可觉察误差(JND)设计自适应扰动阈值,对图像不同像素点位置设置不同的扰动强度,从而增强扰动的人眼不可感知性.此外,还设计了一种数据增强方式对反取证人脸进行数据分布多样性扩充,以进一步提升攻击迁移性.实验结果表明,与6种基线方法相比,所提方法生成的反取证人脸在保证扰动对人眼不可感知前提下具有更强的攻击迁移性. |
| Abstract_FL | Aiming at the insufficient attack transferability of existing generative adversarial network(GAN)-generated face anti-forensics methods,a GAN-generated face anti-forensics method based on image wavelet domain adaptive perturbations is proposed to improve the attack transferability.The proposed method resists the forensic models by adding perturbations to the wavelet domain information of GAN-generated facial ima-ges,which are the frequency components after the image wavelet decomposition.Furthermore,adaptive per-turbation thresholds are designed based on just noticeable distortion(JND)in both the spatial and frequency domains,setting different perturbation strengths for different pixel positions in the image,and thereby enhan-cing the imperceptibility of the perturbations to the human eyes.In addition,a data argumentation approach is designed to expand the distribution diversity of the anti-forensics image,thereby further improving the attack transferability.Experimental results show that compared with the six baseline methods,the anti-forensics im-age generated by the proposed method can achieve stronger attack transferability while ensuring the perturba-tion imperceptibility to the human eyes. |
| Author | 李玉茹 舒华忠 陈北京 |
| AuthorAffiliation | 南京信息工程大学计算机学院,南京 210044;南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京 210044%南京信息工程大学计算机学院,南京 210044%东南大学影像科学与技术实验室,南京 210096 |
| AuthorAffiliation_xml | – name: 南京信息工程大学计算机学院,南京 210044;南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京 210044%南京信息工程大学计算机学院,南京 210044%东南大学影像科学与技术实验室,南京 210096 |
| Author_FL | Li Yuru Shu Huazhong Chen Beijing |
| Author_FL_xml | – sequence: 1 fullname: Chen Beijing – sequence: 2 fullname: Li Yuru – sequence: 3 fullname: Shu Huazhong |
| Author_xml | – sequence: 1 fullname: 陈北京 – sequence: 2 fullname: 李玉茹 – sequence: 3 fullname: 舒华忠 |
| BookMark | eNo9jz9Lw0Achm-oYK39FoJT4u_uckluklK0CkUXncsluZMWuYKH2NE_BXXQOBQHHQKOLhZdNIOfppfGb2FEcXrhHd73eZZQTQ-1RGgFg0u5z9cGbt8Y7WIA7AAD5hIgnlslUKih-n-_iJrG9CPAhHAgxK-jdZvls_zWPn7ai9RO0-LtyWZZefn8dXpu84n9eC2up_OHcae1M59kxdXdLM_L8btNb2x6X76cLaMFJQ6NbP5lA-1vbuy1t5zubme73eo6BgMBx-MhCSEMExkFklfMzKNUVhhMREp5AU9UwGisPCIki8Mg5NinAidR7IvEl4I20Orv7onQSuiD3mB4fKSrx16ik9Eo-hGuDCnQb4sbY9s |
| ClassificationCodes | TP391.4 |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.3969/j.issn.1001-0505.2024.05.030 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | GAN-generated face anti-forensics based on image wavelet domain adaptive perturbation |
| EndPage | 1338 |
| ExternalDocumentID | dndxxb202405030 |
| GrantInformation_xml | – fundername: 国家自然科学基金 funderid: (62072251) |
| GroupedDBID | 2B. 4A8 92I 93N ADMLS ALMA_UNASSIGNED_HOLDINGS PSX TCJ |
| ID | FETCH-LOGICAL-s1020-49828088deb7e93965433e1225abff479df753cf42ae5c8789163a1dbc6ad6ea3 |
| ISSN | 1001-0505 |
| IngestDate | Thu May 29 04:08:38 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Keywords | 离散小波变换(DWT) adversarial perturbations just noticeable distortion GAN-generated face anti-forensics 最小可觉察误差 对抗扰动 GAN生成人脸 反取证 discrete wavelet transform(DWT) |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s1020-49828088deb7e93965433e1225abff479df753cf42ae5c8789163a1dbc6ad6ea3 |
| PageCount | 9 |
| ParticipantIDs | wanfang_journals_dndxxb202405030 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-09-01 |
| PublicationDateYYYYMMDD | 2024-09-01 |
| PublicationDate_xml | – month: 09 year: 2024 text: 2024-09-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | 东南大学学报（自然科学版） |
| PublicationTitle_FL | Journal of Southeast University(Natural Science Edition) |
| PublicationYear | 2024 |
| Publisher | 南京信息工程大学计算机学院,南京 210044 南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京 210044%南京信息工程大学计算机学院,南京 210044%东南大学影像科学与技术实验室,南京 210096 |
| Publisher_xml | – name: 南京信息工程大学江苏省大气环境与装备技术协同创新中心,南京 210044%南京信息工程大学计算机学院,南京 210044%东南大学影像科学与技术实验室,南京 210096 – name: 南京信息工程大学计算机学院,南京 210044 |
| SSID | ssib012290226 ssib002258162 ssib036435511 ssib008679709 ssib023167012 ssib000947520 ssib021009659 ssib057620145 ssib000969306 ssib001128997 ssib006563446 ssib002039847 ssib006703054 ssib051368071 ssib004675274 |
| Score | 2.4030776 |
| Snippet | TP391.4;... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 1330 |
| Title | 基于图像小波域自适应干扰的GAN生成人脸反取证 |
| URI | https://d.wanfangdata.com.cn/periodical/dndxxb202405030 |
| Volume | 54 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR27bhQxcJWHhGgQCBBvpYgrdOHWb1fIe7dHhEgaEildtHu7C9UhkYsUpeIRCSjgKCIKKE6ipCGCBq6g4FuySfgLZnybOwMRL-lkzdmeGc_Mru3x2uMgmC1YAuMQuCWpyooaT6WpGZzIFYqlhSoypgWed15YlPPL_OaKWJmY_OrtWlrvpnPtzSPPlfyPVSEP7IqnZP_BsiOikAEw2BdSsDCkf2VjEgtiWiSyJOaY6tjlRCRygGZEtxCI6g6QJGLE0goLfrEmWhEL6AZ3PGhXBHQMd4AhEUUsbZBCrIgBFvyGXXQwdxSgVBNTrxqALQGaAGvXgBbRzQowEoss5IT-hNghAoWGq9YkRiFgObFDoEms9ABgZ4kVJAapG8h6LIJyfCUCgGtCD0uhCFh5iDVa-0C5zbAEmDcccyfHOCAlsjRNp1mFKRBClg3QzriKdkqglQhDK0QtYuv-mgrlo01jw7fAk7hi6gDAC52gIWoLKSknMaTAJzpKPaDX2GEpBJCgRI2iNUZ1nKRgfNr4le9V6iL6eQOU2wIn6sIfwQT33lThDUchqz565Yd_9VHDJjPSuGETWcyNWMyhalxc20MqPwQmzzrZxkaKdTCmUH0ymKZK4VaJadtcuHXbm8RzJXynxOD1m37QQnT6vUWDOjP-t3sYcXQo_SB0QM5zWsAjYf6ihnSD2LgcQ0p6QQpDvOHAczpQw_6dCRRjQ3hOAIM5u_CC-ImQSe05UeCwU_w277ZVVJo7FsxWar32O6W6g4KdIunc8ea0SyeDE5UzOmOHPcupYGLz7ungetkf7A5elG--lI975U5v7-Pbst8_ePLu24NH5WC7_Pxh79nO_ust6Af2t_t7T1_uDgYHW5_K3vOy9-rg_cMzwXIrXmrM16prVmprIfbS3GiqYbKR5anKDTRacMZyUJNI0qLgymSFEqxdcJrkoq2VBo-SJWGWtmWSyTxhZ4Opzr1Ofi6YyaTOeCJzRdspT0yahgWlWiRZAn5eQs35YKYSeLXqRtdWf3qMLvy5ysXg-PilvRRMde-v55fBNeimV6pn7zsJF8J7 |
| linkProvider | EBSCOhost |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E5%9B%BE%E5%83%8F%E5%B0%8F%E6%B3%A2%E5%9F%9F%E8%87%AA%E9%80%82%E5%BA%94%E5%B9%B2%E6%89%B0%E7%9A%84GAN%E7%94%9F%E6%88%90%E4%BA%BA%E8%84%B8%E5%8F%8D%E5%8F%96%E8%AF%81&rft.jtitle=%E4%B8%9C%E5%8D%97%E5%A4%A7%E5%AD%A6%E5%AD%A6%E6%8A%A5%EF%BC%88%E8%87%AA%E7%84%B6%E7%A7%91%E5%AD%A6%E7%89%88%EF%BC%89&rft.au=%E9%99%88%E5%8C%97%E4%BA%AC&rft.au=%E6%9D%8E%E7%8E%89%E8%8C%B9&rft.au=%E8%88%92%E5%8D%8E%E5%BF%A0&rft.date=2024-09-01&rft.pub=%E5%8D%97%E4%BA%AC%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%A4%A7%E5%AD%A6%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E4%BA%AC+210044&rft.issn=1001-0505&rft.volume=54&rft.issue=5&rft.spage=1330&rft.epage=1338&rft_id=info:doi/10.3969%2Fj.issn.1001-0505.2024.05.030&rft.externalDocID=dndxxb202405030 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fdndxxb%2Fdndxxb.jpg |