Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction
Privacy security and property rights protection have gradually attracted the attention of people. Users not only hope that the images edited by themselves will not be forensically investigated, but also hope that the images they share will not be tampered with. Aiming at the problem that inpainted i...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/15/2/393 |
| _version_ | 1797618047855362048 |
|---|---|
| author | Liyun Dou Guorui Feng Zhenxing Qian |
| author_facet | Liyun Dou Guorui Feng Zhenxing Qian |
| author_sort | Liyun Dou |
| collection | DOAJ |
| description | Privacy security and property rights protection have gradually attracted the attention of people. Users not only hope that the images edited by themselves will not be forensically investigated, but also hope that the images they share will not be tampered with. Aiming at the problem that inpainted images can be located by forensics, this paper proposes a general anti-forensics framework for image inpainting with copyright protection. Specifically, we employ a hierarchical attention model to symmetrically reconstruct the inpainting results based on existing deep inpainting methods. The hierarchical attention model consists of a structural attention stream and a texture attention stream in parallel, which can fuse hierarchical features to generate high-quality reconstruction results. In addition, the user’s identity information can be symmetrically embedded and extracted to protect copyright. The experimental results not only had high-quality structural texture information, but also had homologous features with the original region, which could mislead the detection of forensics analysis. At the same time, the protection of users’ privacy and property rights is also achieved. |
| first_indexed | 2024-03-11T08:04:40Z |
| format | Article |
| id | doaj.art-357fea34ecc94907a55c811e5a01c05f |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-11T08:04:40Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-357fea34ecc94907a55c811e5a01c05f2023-11-16T23:32:44ZengMDPI AGSymmetry2073-89942023-02-0115239310.3390/sym15020393Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical ReconstructionLiyun Dou0Guorui Feng1Zhenxing Qian2School of Communication & Information Engineering, Shanghai University, Shanghai 200444, ChinaSchool of Communication & Information Engineering, Shanghai University, Shanghai 200444, ChinaShanghai Institute of Intelligent Electronics & Systems, School of Computer Science, Fudan University, Shanghai 200433, ChinaPrivacy security and property rights protection have gradually attracted the attention of people. Users not only hope that the images edited by themselves will not be forensically investigated, but also hope that the images they share will not be tampered with. Aiming at the problem that inpainted images can be located by forensics, this paper proposes a general anti-forensics framework for image inpainting with copyright protection. Specifically, we employ a hierarchical attention model to symmetrically reconstruct the inpainting results based on existing deep inpainting methods. The hierarchical attention model consists of a structural attention stream and a texture attention stream in parallel, which can fuse hierarchical features to generate high-quality reconstruction results. In addition, the user’s identity information can be symmetrically embedded and extracted to protect copyright. The experimental results not only had high-quality structural texture information, but also had homologous features with the original region, which could mislead the detection of forensics analysis. At the same time, the protection of users’ privacy and property rights is also achieved.https://www.mdpi.com/2073-8994/15/2/393anti-forensicsimage inpaintingreconstruction |
| spellingShingle | Liyun Dou Guorui Feng Zhenxing Qian Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction Symmetry anti-forensics image inpainting reconstruction |
| title | Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction |
| title_full | Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction |
| title_fullStr | Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction |
| title_full_unstemmed | Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction |
| title_short | Image Inpainting Anti-Forensics Network via Attention-Guided Hierarchical Reconstruction |
| title_sort | image inpainting anti forensics network via attention guided hierarchical reconstruction |
| topic | anti-forensics image inpainting reconstruction |
| url | https://www.mdpi.com/2073-8994/15/2/393 |
| work_keys_str_mv | AT liyundou imageinpaintingantiforensicsnetworkviaattentionguidedhierarchicalreconstruction AT guoruifeng imageinpaintingantiforensicsnetworkviaattentionguidedhierarchicalreconstruction AT zhenxingqian imageinpaintingantiforensicsnetworkviaattentionguidedhierarchicalreconstruction |