Blind PDF Document Watermarking Robust Against PCA and ICA Attacks

Hatoum, Makram; Darazi, Rony; Couchot, Jean

doi:10.5220/0006899605860593

Cited by 5 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…STDM [40,41,42], a special case of QIM [5], spreads the embedding-induced distortion into a group of samples instead of one sample. The embedding function of STDM is as follows:…”

Section: Watermarking Schemesmentioning

confidence: 99%

Using Deep learning for image watermarking attack

Hatoum¹,

Couchot²,

Couturier³

et al. 2021

Signal Processing: Image Communication

Self Cite

View full text Add to dashboard Cite

Digital image watermarking has justified its suitability for copyright protection and copy control of digital images. In the past years, various watermarking schemes were proposed to enhance the fidelity and the robustness of watermarked images against different types of attacks such as additive noise, filtering, and geometric attacks. It is highly important to guarantee a sufficient level of robustness of watermarked images against such type of attacks. Recently, Deep learning and neural networks achieved noticeable development and improvement, especially in image processing, segmentation, and classification. Therefore, in this paper, we studied the effect of a Fully Convolutional Neural Network (FCNN), as a denoising attack, on watermarked images. This deep architecture improves the training process and denoising performance, through which the encoder-decoder remove the noise while preserving the detailed structure of the image. FCNNDA outperforms the other types of attacks because it destroys the watermarks while preserving a good quality of the attacked images. Spread Transform Dither Modulation (STDM) and Spread Spectrum (SS) are used as watermarking schemes to embed the watermarks in the images using several scenarios. This evaluation shows that such type of denoising attack preserves the image quality while breaking the robustness of all evaluated watermarked schemes. It could also be considered a deleterious attack.

show abstract

“…STDM [40,41,42], a special case of QIM [5], spreads the embedding-induced distortion into a group of samples instead of one sample. The embedding function of STDM is as follows:…”

Section: Watermarking Schemesmentioning

confidence: 99%

Using Deep learning for image watermarking attack

Hatoum¹,

Couchot²,

Couturier³

et al. 2021

Signal Processing: Image Communication

Self Cite

View full text Add to dashboard Cite

show abstract

“…Aside from digital images, electronic documents such as PDF files are widely exchanged over the internet, and they are subject to illegal copying and redistribution due to the effortless copying and distributing. Therefore, it has become more important to protect PDF files from any malicious user [17]. Few methods are proposed for hiding information in PDF files.…”

Section: Related Workmentioning

confidence: 99%

Normalized blind STDM watermarking scheme for images and PDF documents robust against fixed gain attack

Hatoum

Darazi

Couchot

2019

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Spread Transform Dither Modulation (STDM), a special case of Quantization Index Modulation (QIM), has been widely used in digital watermarking. STDM has good performance in robustness against re-quantization and random noise attacks, but it is largely vulnerable to the Fixed Gain Attack (FGA). In addition to digital images and videos watermarking applications, copyright protection for digital text such as Portable Document Format (PDF) has received particular attention and interest. In this paper, we modify the STDM watermarking scheme by making the quantization step dependent on the original samples during the embedding process and on the watermarked samples during the decoding process to resist the FGA attack and enhance the robustness against the Additive White Gaussian Noise (AWGN) attack and JPEG compression attack in both the spatial domain and frequency domain regardless of the source of elements used as cover work. Experimentations have been conducted distinctly on digital images and text PDF documents. The tested images were watermarked with a uniform fidelity, where SSIM is fixed to 0.982 and 0.953. Our approach achieves significant robustness against the FGA attack with an improvement of 98% in terms of Bit Error Rates (BER) compared to traditional STDM. As for the AWGN attack, an improvement of 21% is shown. The proposed method also presents robustness against a variety of filtering and geometric attacks, while preserving a high level of transparency.

show abstract

“…In past steganography, cryptography and information hiding techniques were used to solve the copyright issues [6]. Nowadays, digital watermarking gives a better solution for copyright protection with secret 101 information called watermark embedded in digital content [7,8]. The watermark is used for ownership verification when illegal use of digital content happens.…”

Section: Introductionmentioning

confidence: 99%

A Secure Digital Text Watermarking Algorithm for Portable Document Format (PDF)

Khadim¹,

Iqbal²,

Azam³

2022

murjet

View full text Add to dashboard Cite

Nowadays, with the rapid development of advanced technologies, an illegal copy of digital documents can be easily generated. The Portable Document Format is the most common and widely used text document on the internet. The copyright protection of these documents is a challenging task. Advanced techniques have been proposed in the past but have not delivered the expected results. These techniques are either robust or imperceptible or have a high capacity, but do not maintain the balance between all parameters. Digital watermarking has been used over the past decade to detect forgery and tampering detection, maintain copyright and authentication. This study proposes a novel approach for Portable Document Format based on document page objects. The Special objects of Portable Document Format are used for watermarking without affecting the content of the original document. The proposed technique preserves the imperceptibility and resists against formatting attacks. The watermark information is extracted with high probability, the proposed technique is robust, secured, imperceptible, and embeds 0.22 KB of the watermark in the host document.

show abstract

Blind PDF Document Watermarking Robust Against PCA and ICA Attacks

Cited by 5 publications

References 0 publications

Using Deep learning for image watermarking attack

Using Deep learning for image watermarking attack

Normalized blind STDM watermarking scheme for images and PDF documents robust against fixed gain attack

A Secure Digital Text Watermarking Algorithm for Portable Document Format (PDF)

Contact Info

Product

Resources

About