Robust watermarking using diffusion of logo into auto-encoder feature maps

Jamali, Maedeh; Karimi, Nader; Khadivi, Pejman; Shirani, Shahram; Samavi, Shadrokh

doi:10.1007/s11042-023-15371-4

Cited by 1 publication

(2 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the original image is unnecessary during extraction, it is often omitted to output only the watermark. Furthermore, AE with convolutional neural networks has been proposed [ 7 ]. An adversarial network has also been added to improve image quality [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Neural-Network-Based Watermarking Method Approximating JPEG Quantization

Yamauchi,

Kawamura

2024

J. Imaging

View full text Add to dashboard Cite

We propose a neural-network-based watermarking method that introduces the quantized activation function that approximates the quantization of JPEG compression. Many neural-network-based watermarking methods have been proposed. Conventional methods have acquired robustness against various attacks by introducing an attack simulation layer between the embedding network and the extraction network. The quantization process of JPEG compression is replaced by the noise addition process in the attack layer of conventional methods. In this paper, we propose a quantized activation function that can simulate the JPEG quantization standard as it is in order to improve the robustness against the JPEG compression. Our quantized activation function consists of several hyperbolic tangent functions and is applied as an activation function for neural networks. Our network was introduced in the attack layer of ReDMark proposed by Ahmadi et al. to compare it with their method. That is, the embedding and extraction networks had the same structure. We compared the usual JPEG compressed images and the images applying the quantized activation function. The results showed that a network with quantized activation functions can approximate JPEG compression with high accuracy. We also compared the bit error rate (BER) of estimated watermarks generated by our network with those generated by ReDMark. We found that our network was able to produce estimated watermarks with lower BERs than those of ReDMark. Therefore, our network outperformed the conventional method with respect to image quality and BER.

show abstract

Section: Introductionmentioning

confidence: 99%

“…It can find non-significant regions that are insensitive to the human eye and increases robustness by embedding the watermark with larger intensities. Thus, end-to-end models were proposed [ 6 , 7 , 8 , 9 , 10 , 11 ]. However, a huge training dataset was needed to train the connections as the network became more complex.…”

Section: Introductionmentioning

confidence: 99%

A Neural-Network-Based Watermarking Method Approximating JPEG Quantization

Yamauchi,

Kawamura

2024

J. Imaging

View full text Add to dashboard Cite

show abstract

Robust watermarking using diffusion of logo into auto-encoder feature maps

Cited by 1 publication

References 43 publications

A Neural-Network-Based Watermarking Method Approximating JPEG Quantization

A Neural-Network-Based Watermarking Method Approximating JPEG Quantization

Contact Info

Product

Resources

About