Loading [a11y]/accessibility-menu.js
Deep Learning-Based Dual Watermarking for Image Copyright Protection and Authentication | IEEE Journals & Magazine | IEEE Xplore

Deep Learning-Based Dual Watermarking for Image Copyright Protection and Authentication


Impact Statement:Watermarking is widely used for authentication and copyright protection. Lately, deep learning has been leveraged to perform watermarking, which yields a higher accuracy....Show More

Abstract:

Advancements in digital technologies make it easy to modify the content of digital images. Hence, ensuring digital images’ integrity and authenticity is necessary to prot...Show More
Impact Statement:
Watermarking is widely used for authentication and copyright protection. Lately, deep learning has been leveraged to perform watermarking, which yields a higher accuracy. However, existing deep learning techniques can only perform either authentication or copyright protection and are vulnerable to overwriting and surrogate model attacks. In this work, we used deep learning to perform image copyright protection and authentication simultaneously while achieving a high level of accuracy, performance and robustness against content-preserving image manipulation attacks, overwriting attack and surrogate model attack. The watermarked images are indistinguishable from the original image, with an average peak signal-to-noise ratio (PSNR) of 46.87 dB and structural similarity index measure (SSIM) of 0.95 while maintaining a high accuracy of 96% for copyright protection and 94% accuracy for authenticating images.

Abstract:

Advancements in digital technologies make it easy to modify the content of digital images. Hence, ensuring digital images’ integrity and authenticity is necessary to protect them against various attacks that manipulate them. We present a deep learning (DL) based dual invisible watermarking technique for performing source authentication, content authentication, and protecting digital content copyright of images sent over the internet. Beyond securing images, the proposed technique demonstrates robustness to content-preserving image manipulation attacks. It is also impossible to imitate or overwrite watermarks because the cryptographic hash of the image and the dominant features of the image in the form of perceptual hash are used as watermarks. We highlighted the need for source authentication to safeguard image integrity and authenticity, along with identifying similar content for copyright protection. After exhaustive testing, our technique obtained a high peak signal-to-noise ratio (...
Published in: IEEE Transactions on Artificial Intelligence ( Volume: 5, Issue: 12, December 2024)
Page(s): 6134 - 6145
Date of Publication: 24 October 2024
Electronic ISSN: 2691-4581

Funding Agency:


References

References is not available for this document.