Fixing the Double Agent Vulnerability of Deep Watermarking: A Patch-Level Solution against Artwork Plagiarism

• Published in: IEEE transactions on circuits and systems for video technology Vol. 34; no. 3; p. 1
• Main Authors: Luo, Yuanjing, Zhou, Tongqing, Cui, Shenglan, Ye, Yunfan, Liu, Fang, Cai, Zhiping
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.03.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Art works; artwork copyright protection; convolutional neural networks; Copy protection; Copyright protection; Decoding; Deep watermarking; Distortion; Embedding; Encoders-Decoders; Plagiarism; plagiarism resistance; Robustness; Training; Watermarking

Increasing artwork plagiarism incidents stresses the urgent need for proper Copyright protection on behalf of the creators. The latest development in this context focuses on embedding watermarks via deep encoder-decoder networks. However, we find that deep watermarking has a serious vulnerability on...