Deep learning technologies, which are the key components of state-of-the-art Artificial Intelligence (AI) services, have shown great success in providing human-level capabilities for a variety of tasks, such as visual analysis, speech recognition, and natural language processing and etc. Building a production-level deep learning model is a non-trivial task, which requires a large amount of training data, powerful computing resources, and human expertises. Therefore, illegitimate reproducing, distribution, and the derivation of proprietary deep learning models can lead to copyright infringement and economic harm to model creators. Therefore, it is essential to devise a technique to protect the intellectual property of deep learning models and enable external verification of the model ownership. In this paper, we generalize the "digital watermarking'' concept from multimedia ownership verification to deep neural network (DNNs) models. We investigate three DNN-applicable watermark generation algorithms, propose a watermark implanting approach to infuse watermark into deep learning models, and design a remote verification mechanism to determine the model ownership. By extending the intrinsic generalization and memorization capabilities of deep neural networks, we enable the models to learn specially crafted watermarks at training and activate with pre-specified predictions when observing the watermark patterns at inference. We evaluate our approach with two image recognition benchmark datasets. Our framework accurately (100%) and quickly verifies the ownership of all the remotely deployed deep learning models without affecting the model accuracy for normal input data. In addition, the embedded watermarks in DNN models are robust and resilient to different counter-watermark mechanisms, such as fine-tuning, parameter pruning, and model inversion attacks.

Protecting Intellectual Property of Deep Neural Networks with Watermarking

In this paper, a novel robust color image watermarking method based on Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) is proposed. In this method, RGB cover image is divided into red, green and blue components. DCT and DWT are applied to each color components. Grayscale watermark image is scrambled by using Arnold transform. DCT is performed to the scrambled watermark image. Transformed watermark image is then divided into equal smaller parts. DCT coefficients of each watermark parts are embedded into four DWT bands of the color components of the cover image. The robustness of the proposed color image watermarking has been demonstrated by applying various image processing operations such as rotating, resizing, filtering, jpeg compression, and noise adding to the watermarked images. Experimental results show that the proposed method is robust to the linear and nonlinear attacks and the transparency of the watermarked images has been protected.

A novel hybrid DCT and DWT based robust watermarking algorithm for color images

Wavelet transform based on Meyer algorithm for image edge and blocking artifact reduction

Digital watermarking is a branch of steganography, which is used to secure the copyright ownership of owner of the content available in digital form. It refers to an infrastructure where any digita...

Secured and multi optimized image watermarking using SVD and entropy and prearranged embedding locations in transform domain

In this paper, a new algorithm for multiple digital watermarking is proposed that is based on the combination of lifting wavelet transform (LWT) and discrete cosine transform (DCT) then Arnold transformation for encryption purpose is used. Multiple watermarks are embedded to avoid the chances of identity theft. The algorithm comprises of two parts, watermark embedding and watermark extraction. In embedding part, the cover image is decomposed into four sub bands by applying second level LWT. Low frequency sub bands LL2 and LH2 are then transformed by DCT. Two image watermarks are also transformed using DCT then one of the transformed watermark is again transformed using Arnold and its resultant is known as encrypted watermark. Encrypted watermark is embedded to LL2 sub band and normal DCT transformed to LH2 sub band. Extraction of watermark is performed using extraction algorithm. Watermarked image is subjected to various attacks to check the robustness of the algorithm. Experimental results are provided to demonstrate that the algorithm provides good results.

Multiple image watermarking using LWT, DCT and arnold transformation

In this paper, we suggested a new secured digital watermarking technique that can be used for the data validation. The suggested method is secure and efficient. The secured digital watermark is added by the hybrid method for which we have used combination of discrete cosine transform (DCT) and discrete wavelet transform (DWT) methods along with cryptographic technique (Arnold Transform). This technique provides strong robustness and perception transparency to the watermarked image and original image against different kind of attacks like cropping, noise and scaling. We have also compared these results with Least Significant Bit and Discrete Cosine methods.

V. V. Nath

Papers

Secured digital image watermarking with discrete cosine transform and discrete wavelet transform method