A robust hybrid digital watermarking technique against a powerful CNN-based adversarial attack
- PDF / 5,502,411 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 62 Downloads / 189 Views
A robust hybrid digital watermarking technique against a powerful CNN-based adversarial attack Sai Shyam Sharma1
· V. Chandrasekaran1
Received: 2 September 2019 / Revised: 24 June 2020 / Accepted: 6 August 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Digital watermarking techniques are valuable tools to embed digital signatures on multimedia content to establish the legal ownership and authenticity claims by the owners. Firstly this paper investigates the robustness of popular transform domain-based digital image watermarking schemes such as DCT, SVD, DWT, and their hybrid combinations against known image processing type attacks such as image blurring, compression, noise addition, rotation and cropping. Then, an enhanced hybrid scheme using DWT and SVD methods is proposed and its improved performance is demonstrated in terms of the quality of the extracted watermarks measured in terms of PSNR, SSIM and NCC values. This paper then proposes a novel adversarial attack based on a powerful Deep Convolutional Neural Network based Autoencoder(CAE) scheme. The CAE is specifically chosen to exploit its intrinsic capability to represent the image content (spatial and structural) through lower dimensional projections in the intermediate layers. The CAE is trained and tested on the entire image repository of the CIFAR10 data set. Once CAE is trained on a class of images and the parameters are frozen, it will serve as a system to produce a perceptually close image for any unseen input image belonging to the same class. The power of the proposed adversarial attack scheme is shown in terms of the quality of extracted watermarks against popular water mark embedding schemes. Finally the proposed enhanced hybrid strategy of DWT+SVD is shown to be robust against the new form of attack and outperforms all other techniques measured in terms of its high quality watermark extraction. Keywords Digital watermarking · Convolutional autoencoder · Copyright protection · Adversarial attacks · Hybrid transforms
1 Introduction The proliferation of multimedia data in the form of images and videos are a boon and a curse. WhatsApp, Facebook, Instagram, Twitter and Snapchat are some of the most popular platforms that have millions of active users contributing petabytes of image data on a Sai Shyam Sharma
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
daily basis. Easy misuse of this data emphasizes the relevance of image forensics today. The technologies used for representation, storage and transmission of multimedia files are a major challenge for media forensics [8]. Digital watermarking and steganography methods have been used for multimedia security. Both steganography and digital watermarking hide information in the cover data. Steganography techniques are applied in covert communication or message passing while watermarking methods are used for copyright protection, authentication, counterfeit protection, traito
Data Loading...
