Yuhang Meng¹, Xianyi Chen^1,*, Xingming Sun¹, Yu Liu¹, Guo Wei²

CMC-Computers, Materials & Continua, Vol.75, No.1, pp. 831-844, 2023, DOI:10.32604/cmc.2023.033700

Abstract Image processing networks have gained great success in many fields, and thus the issue of copyright protection for image processing networks has become a focus of attention. Model watermarking techniques are widely used in model copyright protection, but there are two challenges: (1) designing universal trigger sample watermarking for different network models is still a challenge; (2) existing methods of copyright protection based on trigger s watermarking are difficult to resist forgery attacks. In this work, we propose a dual model watermarking framework for copyright protection in image processing networks. The trigger sample watermark is embedded in the training process… More >

Tao Chen¹, Zhao Qiu^1,*, Gengquan Xie¹, Lin Yuan¹, Shaohua Duan¹, Hao Guo¹, Dahao Fu¹, Hancheng Huang²

Journal of Information Hiding and Privacy Protection, Vol.3, No.3, pp. 131-142, 2021, DOI:10.32604/jihpp.2021.026606

Abstract Behind the popularity of multimedia technology, the dispute over image copyright is getting worse. In the digital watermark prevention technology for copyright infringement, watermark technology is considered to be an important technology to overcome data protection problems and verify the relationship between data ownership. Among the many digital watermarking technologies, zero watermarking technology has been favored in recent years. However, the existing zero watermark technology in the implementation process often needs a trusted third party to store watermarks, which may make the data too central, data storage security is low and copyright registration costs are too high, which creates a… More >

Baowei Wang^1,2,3,*, Weishen Wang¹, Peng Zhao¹, Naixue Xiong⁴

CMC-Computers, Materials & Continua, Vol.71, No.2, pp. 2633-2652, 2022, DOI:10.32604/cmc.2022.022291

Abstract Most of the existing zero-watermark schemes for medical images are only appropriate for a single grayscale image. When they protect a large number of medical images, repeating operations will cause a significant amount of time and storage costs. Hence, this paper proposes an efficient zero-watermark scheme for multiple color medical images based on quaternion generalized Fourier descriptor (QGFD). Firstly, QGFD is utilized to compute the feature invariants of each color image, then the representative features of each image are selected, stacked, and reshaped to generate a feature matrix, which is then binarized to get a binary feature image. Copyright information… More >

Ahmed S. Alghamdi¹, Surayya Naz², Ammar Saeed³, Eesa Al Solami¹, Muhammad Kamran^1,*, Mohammed Saeed Alkatheiri¹

CMC-Computers, Materials & Continua, Vol.70, No.1, pp. 1585-1601, 2022, DOI:10.32604/cmc.2022.019936

Abstract With widespread use of relational database in various real-life applications, maintaining integrity and providing copyright protection is gaining keen interest of the researchers. For this purpose, watermarking has been used for quite a long time. Watermarking requires the role of trusted third party and a mechanism to extract digital signatures (watermark) to prove the ownership of the data under dispute. This is often inefficient as lots of processing is required. Moreover, certain malicious attacks, like additive attacks, can give rise to a situation when more than one parties can claim the ownership of the same data by inserting and detecting… More >

Lulu Cui^2,3,*, Yabin Xu^1,2,3

Journal on Big Data, Vol.2, No.2, pp. 53-62, 2020, DOI:10.32604/jbd.2020.010590

Abstract In order to effectively solve the problem of copyright protection of materials genome engineering data, this paper proposes a method for copyright protection of materials genome engineering data based on zero-watermarking technology. First, the important attribute values are selected from the materials genome engineering database; then, use the method of remainder to group the selected attribute values and extract eigenvalues; then, the eigenvalues sequence is obtained by the majority election method; finally, XOR the sequence with the actual copyright information to obtain the watermarking information and store it in the third-party authentication center. When a copyright dispute requires copyright authentication… More >