Robust Adversarial Watermark Defending Against GAN Synthesization Attack
文献类型：期刊论文
| 作者 | Xu, Shengwang1; Qiao, Tong1,2,3; Xu, Ming1; Wang, Wei4 ; Zheng, Ning1
|
| 刊名 | IEEE SIGNAL PROCESSING LETTERS
 |
| 出版日期 | 2024 |
| 卷号 | 31页码:351-355 |
| 关键词 | Watermarking Transform coding Generative adversarial networks Forgery Image coding Discrete cosine transforms Decoding GAN synthesized image adversarial watermark JPEG compression |
| ISSN号 | 1070-9908 |
| DOI | 10.1109/LSP.2024.3350983 |
| 通讯作者 | Qiao, Tong(tong.qiao@hdu.edu.cn) ; Xu, Ming(mxu@hdu.edu.cn) |
| 英文摘要 | The proliferation of facial manipulation has been propelled by generative adversarial networks (GAN), severely threatening to the personal privacy and reputation. Accordingly, one such countermeasure is adversarial watermark, which is embedded into the protected image prior to GAN synthesization attack, resulting into the distorted fake content obtained by malicious attackers. However, in practice, JPEG compression usually causes a remarkable degradation on the performance of adversarial watermark. To address this challengeable issue, this letter presents a novel robust adversarial watermark, which can effectively defend against GAN synthesization attack, even though suffering from JPEG compression. Extensive experiments verify the superiority of our proposed method in the benchmark dataset; more importantly, the robustness of the proposed adversarial watermark is comprehensively evaluated on the both simulated transmission channel and the realism social network platform. |
| WOS关键词 | FAKE ; DEFENSE |
| 资助项目 | Zhejiang Provincial Natural Science Foundation of China |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:001166563800004 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Zhejiang Provincial Natural Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57841]  |
| 专题 | 多模态人工智能系统全国重点实验室 |
| 通讯作者 | Qiao, Tong; Xu, Ming |
| 作者单位 | 1.Hangzhou Dianzi Univ, Sch Cyberspace, Hangzhou 310018, Peoples R China 2.Sino France Joint Lab Digital Media Forens Zhejian, Hangzhou 310018, Peoples R China 3.Chinese Acad Sci, Inst Informat Engn, State Key Lab Informat Secur, Beijing 100093, Peoples R China 4.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, State Key Lab Multimodal Artificial Intelligence S, Beijing 100080, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xu, Shengwang,Qiao, Tong,Xu, Ming,et al. Robust Adversarial Watermark Defending Against GAN Synthesization Attack[J]. IEEE SIGNAL PROCESSING LETTERS,2024,31:351-355. |
| APA | Xu, Shengwang,Qiao, Tong,Xu, Ming,Wang, Wei,&Zheng, Ning.(2024).Robust Adversarial Watermark Defending Against GAN Synthesization Attack.IEEE SIGNAL PROCESSING LETTERS,31,351-355. |
| MLA | Xu, Shengwang,et al."Robust Adversarial Watermark Defending Against GAN Synthesization Attack".IEEE SIGNAL PROCESSING LETTERS 31(2024):351-355. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。