5 accepted papers
Document protection has become a critical issue for preventing unauthorized copying, distribution, and tampering. Document encryption is a proven solution, but it is not resistant to attacks from the physical world such as screenshots, printing and photographing. A common document protection techniq
Deep watermarking models optimize robustness by incorporating distortions between the encoder and decoder. To tackle non-differentiable distortions, current methods only train the decoder with distorted images, which breaks the joint optimization of the encoder-decoder, resulting in suboptimal perfo…
DNN-based watermarking methods have rapidly advanced, with the ``Encoder-Noise Layer-Decoder'' (END) framework being the most widely used. To ensure end-to-end training, the noise layer in the framework must be differentiable. However, real-world distortions are often non-differentiable, leading to…
Recent developments in DNN-based image watermarking techniques have achieved impressive results in protecting digital content. However, most existing methods are constrained to low-resolution images as they need to encode the entire image, leading to prohibitive memory and computational costs when a…
Watermarking algorithms based on deep Convolutional Neural Networks (CNN) have been extensively studied and shown to effectively improve performance. Most deep watermarking algorithms are dependent on the participation of host images, which results in more time and computing resources for embedding…