Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal

被引:5
|
作者
Liu, Xinwei [1 ,2 ]
Liu, Jian [3 ]
Bai, Yang [4 ]
Gu, Jindong [5 ]
Chen, Tao [3 ]
Jia, Xiaojun [1 ,2 ]
Cao, Xiaochun [1 ,6 ]
机构
[1] Chinese Acad Sci, Inst Informat Engn, SKLOIS, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Sch Cyber Secur, Beijing, Peoples R China
[3] Ant Grp, Beijing, Peoples R China
[4] Tencent Secur Zhuque Lab, Beijing, Peoples R China
[5] Univ Munich, Munich, Germany
[6] Sun Yat Sen Univ, Sch Cyber Sci & Technol, Shenzhen Campus, Shenzhen 518107, Peoples R China
来源
基金
国家重点研发计划;
关键词
Visible watermark removal; Watermark protection; Adversarial attack;
D O I
10.1007/978-3-031-19781-9_1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
As a common security tool, visible watermarking has been widely applied to protect copyrights of digital images. However, recent works have shown that visible watermarks can be removed by DNNs without damaging their host images. Such watermark-removal techniques pose a great threat to the ownership of images. Inspired by the vulnerability of DNNs on adversarial perturbations, we propose a novel defence mechanism by adversarial machine learning for good. From the perspective of the adversary, blind watermark-removal networks can be posed as our target models; then we actually optimize an imperceptible adversarial perturbation on the host images to proactively attack against watermark-removal networks, dubbed Watermark Vaccine. Specifically, two types of vaccines are proposed. Disrupting Watermark Vaccine (DWV) induces to ruin the host image along with watermark after passing through watermark-removal networks. In contrast, Inerasable Watermark Vaccine (IWV) works in another fashion of trying to keep the watermark not removed and still noticeable. Extensive experiments demonstrate the effectiveness of our DWV/IWV in preventing watermark removal, especially on various watermark removal networks.
引用
收藏
页码:1 / 17
页数:17
相关论文
共 50 条
  • [1] Adversarial watermark: A robust and reliable watermark against removal
    Wang, Jinwei
    Huang, Wanyun
    Zhang, Jiawei
    Luo, Xiangyang
    Ma, Bin
    Journal of Information Security and Applications, 2024, 82
  • [2] Adversarial watermark: A robust and reliable watermark against removal
    Wang, Jinwei
    Huang, Wanyun
    Zhang, Jiawei
    Luo, Xiangyang
    Ma, Bin
    JOURNAL OF INFORMATION SECURITY AND APPLICATIONS, 2024, 82
  • [3] Generative adversarial networks model for visible watermark removal
    Cao, Zhiyi
    Niu, Shaozhang
    Zhang, Jiwei
    Wang, Xinyi
    IET IMAGE PROCESSING, 2019, 13 (10) : 1783 - 1789
  • [4] Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples
    Jia, Xiaojun
    Wei, Xingxing
    Cao, Xiaochun
    Han, Xiaoguang
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 1579 - 1587
  • [5] Electronic Map Visible Watermark Removal with Conditional Generative Adversarial Networks
    Jiang B.
    Xu S.
    Wang J.
    Wang M.
    Journal of Geo-Information Science, 2023, 25 (02) : 288 - 297
  • [6] WDNet: Watermark-Decomposition Network for Visible Watermark Removal
    Liu, Yang
    Zhu, Zhen
    Bai, Xiang
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 3684 - 3692
  • [7] FAWA: Fast Adversarial Watermark Attack
    Jiang, Hao
    Yang, Jintao
    Hua, Guang
    Li, Lixia
    Wang, Ying
    Tu, Shenghui
    Xia, Song
    IEEE TRANSACTIONS ON COMPUTERS, 2024, 73 (02) : 301 - 313
  • [8] Watermark detection after quantization attacks
    Eggers, JJ
    Girod, B
    INFORMATION HIDING, PROCEEDINGS, 2000, 1768 : 172 - 186
  • [9] CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes
    Huang, Hao
    Wang, Yongtao
    Chen, Zhaoyu
    Zhang, Yuze
    Li, Yuheng
    Tang, Zhi
    Chu, Wei
    Chen, Jingdong
    Lin, Weisi
    Ma, Kai-Kuang
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 989 - 997
  • [10] Analysis of Digital Image Watermark Attacks
    Song, Chunlin
    Sudirman, Sud
    Merabti, Madjid
    Llewellyn-Jones, David
    2010 7TH IEEE CONSUMER COMMUNICATIONS AND NETWORKING CONFERENCE-CCNC 2010, 2010, : 941 - 945