Showing papers on "Digital watermarking published in 2017"

Embedding Watermarks into Deep Neural Networks

Abstract: Significant progress has been made with deep neural networks recently. Sharing trained models of deep neural networks has been a very important in the rapid progress of research and development of these systems. At the same time, it is necessary to protect the rights to shared trained models. To this end, we propose to use digital watermarking technology to protect intellectual property and detect intellectual property infringement in the use of trained models. First, we formulate a new problem: embedding watermarks into deep neural networks. Second, we propose a general framework for embedding a watermark in model parameters, using a parameter regularizer. Our approach does not impair the performance of networks into which a watermark is placed because the watermark is embedded while training the host network. Finally, we perform comprehensive experiments to reveal the potential of watermarking deep neural networks as the basis of this new research effort. We show that our framework can embed a watermark during the training of a deep neural network from scratch, and during fine-tuning and distilling, without impairing its performance. The embedded watermark does not disappear even after fine-tuning or parameter pruning; the watermark remains complete even after 65% of parameters are pruned.

Embedding Watermarks into Deep Neural Networks

Abstract: Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is necessary to protect the rights of shared trained models. To this end, we propose to use a digital watermarking technology to protect intellectual property or detect intellectual property infringement of trained models. Firstly, we formulate a new problem: embedding watermarks into deep neural networks. We also define requirements, embedding situations, and attack types for watermarking to deep neural networks. Secondly, we propose a general framework to embed a watermark into model parameters using a parameter regularizer. Our approach does not hurt the performance of networks into which a watermark is embedded. Finally, we perform comprehensive experiments to reveal the potential of watermarking to deep neural networks as a basis of this new problem. We show that our framework can embed a watermark in the situations of training a network from scratch, fine-tuning, and distilling without hurting the performance of a deep neural network. The embedded watermark does not disappear even after fine-tuning or parameter pruning; the watermark completely remains even after removing 65% of parameters were pruned. The implementation of this research is: this https URL

A blind medical image watermarking: DWT-SVD based robust and secure approach for telemedicine applications

Abstract: In this paper, a blind image watermarking scheme based on discrete wavelet transform (DWT) and singular value decomposition (SVD) is proposed. In this scheme, DWT is applied on ROI (region of interest) of the medical image to get different frequency subbands of its wavelet decomposition. On the low frequency subband LL of the ROI, block-SVD is applied to get different singular matrices. A pair of elements with similar values is identified from the left singular value matrix of these selected blocks. The values of these pairs are modified using certain threshold to embed a bit of watermark content. Appropriate threshold is chosen to achieve the imperceptibility and robustness of medical image and watermark contents respectively. For authentication and identification of original medical image, one watermark image (logo) and other text watermark have been used. The watermark image provides authentication whereas the text data represents electronic patient record (EPR) for identification. At receiving end, blind recovery of both watermark contents is performed by a similar comparison scheme used during the embedding process. The proposed algorithm is applied on various groups of medical images like X-ray, CT scan and mammography. This scheme offers better visibility of watermarked image and recovery of watermark content due to DWT-SVD combination. Moreover, use of Hamming error correcting code (ECC) on EPR text bits reduces the BER and thus provides better recovery of EPR. The performance of proposed algorithm with EPR data coding by Hamming code is compared with the BCH error correcting code and it is found that later one perform better. A result analysis shows that imperceptibility of watermarked image is better as PSNR is above 43 dB and WPSNR is above 52 dB for all set of images. In addition, robustness of the scheme is better than existing scheme for similar set of medical images in terms of normalized correlation coefficient (NCC) and bit-error-rate (BER). An analysis is also carried out to verify the performance of the proposed scheme for different size of watermark contents (image and EPR data). It is observed from analysis that the proposed scheme is also appropriate for watermarking of color image. Using proposed scheme, watermark contents are extracted successfully under various noise attacks like JPEG compression, filtering, Gaussian noise, Salt and pepper noise, cropping, filtering and rotation. Performance comparison of proposed scheme with existing schemes shows proposed scheme has better robustness against different types of attacks. Moreover, the proposed scheme is also robust under set of benchmark attacks known as checkmark attacks.

Information hiding in medical images: a robust medical image watermarking system for E-healthcare

Abstract: Electronic transmission of the medical images is one of the primary requirements in a typical Electronic-Healthcare (E-Healthcare) system. However this transmission could be liable to hackers who may modify the whole medical image or only a part of it during transit. To guarantee the integrity of a medical image, digital watermarking is being used. This paper presents two different watermarking algorithms for medical images in transform domain. In first technique, a digital watermark and Electronic Patients Record (EPR) have been embedded in both regions; Region of Interest (ROI) and Region of Non-Interest (RONI). In second technique, Region of Interest (ROI) is kept untouched for tele-diagnosis purpose and Region of Non-Interest (RONI) is used to hide the digital watermark and EPR. In either algorithm 8ź×ź8 block based Discrete Cosine Transform (DCT) has been used. In each 8ź×ź8 block two DCT coefficients are selected and their magnitudes are compared for embedding the watermark/EPR. The selected coefficients are modified by using a threshold for embedding bit a `0' or bit `1' of the watermark/EPR. The proposed techniques have been found robust not only to singular attacks but also to hybrid attacks. Comparison results viz-a - viz payload and robustness show that the proposed techniques perform better than some existing state of art techniques. As such the proposed algorithms could be useful for e-healthcare systems.

Improved hybrid algorithm for robust and imperceptible multiple watermarking using digital images

Abstract: This paper presents a new robust hybrid multiple watermarking technique using fusion of discrete wavelet transforms (DWT), discrete cosine transforms (DCT), and singular value decomposition (SVD) instead of applying DWT, DCT and SVD individually or combination of DWT-SVD / DCT-SVD. For identity authentication purposes, multiple watermarks are embedded into the same medical image / multimedia objects simultaneously, which provides extra level of security with acceptable performance in terms of robustness and imperceptibility. In the embedding process, the cover image is decomposed into first level discrete wavelet transforms where the A (approximation/lower frequency sub-band) is transformed by DCT and SVD. The watermark image is also transformed by DWT, DCT and SVD. The S vector of watermark information is embedded in the S component of the cover image. The watermarked image is generated by inverse SVD on modified S vector and original U, V vectors followed by inverse DCT and inverse DWT. The watermark is extracted using an extraction algorithm. Furthermore, the text watermark is embedding at the second level of the D (diagonal sub-band) of the cover image. The security of the text watermark considered as EPR (Electronic Patient Record) data is enhanced by using encryption method before embedding into the cover. The results are obtained by varying the gain factor, size of the text watermark, and cover medical images. The method has been extensively tested and analyzed against known attacks and is found to be giving superior performance for robustness, capacity and reduced storage and bandwidth requirements compared to reported techniques suggested by other authors.

A blind DCT based color watermarking algorithm for embedding multiple watermarks

Abstract: Multiple watermarking based techniques are receiving more attention in recent times for its wide variety of applications in different fields. To protect the copyright ownership and validate the authenticity of multiple owners, in this paper a color multiple watermarking method based on DCT (Discrete Cosine Transform) and repetition code is proposed and simulated. Initially, green and blue components of color host image are selected for inserting multiple watermarks. Then, each green and blue component of the image is decomposed into non overlapping blocks and subsequently DCT is employed on each block. In this technique, a binary bit of watermark is embedded into green/blue component’s transformed block by modifying some middle significant AC coefficients using repetition code. During multiple watermarks embedding in green and blue components of the proposed method, DC and some higher AC coefficients are kept intact after zigzag scanning of each DCT block to ensure the imperceptibility of the watermarked host image. The proposed scheme is experimented to establish the validity by extracting adequate multiple watermark data from the restructured cover image after applying common geometric transformation attacks (like rotation, cropping, scaling and deletion of lines/columns etc.), common enhancement technique attacks (like lowpass filtering, histogram equalization, sharpening, gamma correction, noise addition etc.) and JPEG compression attacks.

DWT-SVD and DCT based robust and blind watermarking scheme for copyright protection

Abstract: In this article, a new DWT-SVD and DCT with Arnold Cat Map encryption based robust and blind watermarking scheme is proposed for copyright protection. The proposed scheme solves the most frequently occurring watermarking security problems in Singular Value Decomposition (SVD) based schemes which are unauthorized reading and false-positive detection. This scheme also optimizes fidelity and robustness characteristics. The grey image watermark splits into two parts using four bits MSBs and four bits LSBs of each pixel. Discrete Cosine Transform (DCT) coefficients of these MSBs and LSBs values are embedded into the middle singular value of each block having size 4 × 4 of the host image's one level Discrete Wavelet Transform (DWT) sub-bands. The reason for incorporating Arnold Cat Map in the proposed scheme is to encode the watermark image before embedding it in the host image. The proposed scheme is a blind scheme and does not require the choice of scaling factor. Thus, the proposed scheme is secure as well as free from the false positive detection problem. The proposed watermarking scheme is tested for various malicious and non-malicious attacks. The experimental results demonstrate that the scheme is robust, imperceptible and secure to several attacks and common signal processing operations.

Digital image watermarking method based on DCT and fractal encoding

Abstract: With the rapid development of computer science, problems with digital products piracy and copyright dispute become more serious; therefore, it is an urgent task to find solutions for these problems. In this study, the authors' develop a digital watermarking algorithm based on a fractal encoding method and the discrete cosine transform (DCT). The proposed method combines fractal encoding method and DCT method for double encryptions to improve traditional DCT method. The image is encoded by fractal encoding as the first encryption, and then encoded parameters are used in DCT method as the second encryption. First, the fractal encoding method is adopted to encode a private image with private scales. Encoding parameters are applied as digital watermarking. Then, digital watermarking is added to the original image to reversibly using DCT, which means the authors can extract the private image from the carrier image with private encoding scales. Finally, attacking experiments are carried out on the carrier image by using several attacking methods. Experimental results show that the presented method has higher performance characteristics such as robustness and peak signal to noise ratio than classical methods.

DCT based efficient fragile watermarking scheme for image authentication and restoration

Abstract: Due to rapid development of Internet and computer technology, image authentication and restoration are very essential, especially when it is utilized in forensic science, medical imaging and evidence of court. A quantization and Discrete Cosine Transform(DCT) based self-embedding fragile watermarking scheme with effective image authentication and restoration quality is proposed in this paper. In this scheme, the cover image is divided in size of 2×2 non-overlapping blocks. For each block twelve bits watermark are generated from the five most significant bits (MSBs) of each pixel and are embedded into the three least significant bits (LSBs) of the pixels corresponding to the mapped block. The proposed scheme uses two levels encoding for content restoration bits generation. The restoration is achievable with high PSNR and NCC up to 50 % tampering rate. The experimental results demonstrate that the proposed scheme not only outperforms high quality restoration effectively, but also removes the blocking artifacts and improves the accuracy of tamper localization due to use of very small size blocks.

Adversarial Frontier Stitching for Remote Neural Network Watermarking

Abstract: The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional neural networks for image classification, by embedding information into their weights. While this is a clear progress towards model protection, this technique solely allows for extracting the watermark from a network that one accesses locally and entirely. Instead, we aim at allowing the extraction of the watermark from a neural network (or any other machine learning model) that is operated remotely, and available through a service API. To this end, we propose to mark the model's action itself, tweaking slightly its decision frontiers so that a set of specific queries convey the desired information. In the present paper, we formally introduce the problem and propose a novel zero-bit watermarking algorithm that makes use of adversarial model examples. While limiting the loss of performance of the protected model, this algorithm allows subsequent extraction of the watermark using only few queries. We experimented the approach on three neural networks designed for image classification, in the context of MNIST digit recognition task.

Reversible data hiding in encrypted images

Abstract: Hiding information in an image in a way that does not affect the original cover image pixels or cause a permanent distortion after extracting that information is known as reversible data hiding technology. Many reversible data hiding schemes have been proposed and successfully applied in medical and military applications. Such schemes are developed to ensure digital images' authenticity and integrity without any distortion on the original images. They guarantee that any attempt to change the watermarked image will be detected by the image owner. In this paper, a novel algorithm is proposed to reversibly hide data into encrypted grayscale medical images in a separable manner. The proposed algorithm hides two watermarks in a given encrypted image. The first watermark is embedded by replacing selected encrypted image pixels based on data hiding key, and the second watermark is embedded in the watermarked encrypted image using the histogram shifting reversible data hiding method. The experimental results demonstrate that the proposed algorithm has high embedding capacity, high visual image quality, and high entropy.

Robust and Secure Multiple Watermarking for Medical Images

Abstract: This paper presents a robust and secure region of interest and non-region of interest based watermarking method for medical images. The proposed method applies the combination of discrete wavelet transform and discrete cosine transforms on the cover medical image for the embedding of image and electronic patient records (EPR) watermark simultaneously. The embedding of multiple watermarks at the same time provides extra level of security and important for the patient identity verification purpose. Further, security of the image and EPR watermarks is enhancing by using message-digest (MD5) hash algorithm and Rivest---Shamir---Adleman respectively before embedding into the medical cover image. In addition, Hamming error correction code is applying on the encrypted EPR watermark to enhance the robustness and reduce the possibility bit error rates which may result into wrong diagnosis in medical environments. The robustness of the method is also extensively examined for known attacks such as salt & pepper, Gaussian, speckle, JPEG compression, filtering, histogram equalization. The method is found to be robust for hidden watermark at acceptable quality of the watermarked image. Therefore, the hybrid method is suitable for avoidance of the patient identity theft/alteration/modification and secure medical document dissemination over the open channel for medical applications.

Quantum watermarking scheme through Arnold scrambling and LSB steganography

Abstract: Based on the NEQR of quantum images, a new quantum gray-scale image watermarking scheme is proposed through Arnold scrambling and least significant bit (LSB) steganography. The sizes of the carrier image and the watermark image are assumed to be $$2n\times 2n$$ and $$n\times n$$ , respectively. Firstly, a classical $$n\times n$$ sized watermark image with 8-bit gray scale is expanded to a $$2n\times 2n$$ sized image with 2-bit gray scale. Secondly, through the module of PA-MOD N, the expanded watermark image is scrambled to a meaningless image by the Arnold transform. Then, the expanded scrambled image is embedded into the carrier image by the steganography method of LSB. Finally, the time complexity analysis is given. The simulation experiment results show that our quantum circuit has lower time complexity, and the proposed watermarking scheme is superior to others.

A robust blind hybrid image watermarking scheme in RDWT-DCT domain using Arnold scrambling

Abstract: To compromise between imperceptibility and robustness property of robust image watermarking technique, a RDWT-DCT based blind image watermarking scheme using Arnold scrambling is presented in this paper. Firstly, RDWT (Redundant Discrete Wavelet Transform) is applied to each gray scale cover image block after the image is decomposed into fixed size non overlapping blocks. Secondly, the binary watermark logo is encrypted by Arnold chaotic map and reshaped to a sequence to improve the security of the logo. In the subsequent step, DCT (Discrete Cosine Transform) is employed on each LH subband of the non-overlapping host image block. Finally, after zigzag scanning of each DCT block a binary bit of watermark is embedded into each block by adjusting some middle significant AC coefficients using repetition code. Experimental results show that robustness is achieved by recovering satisfactory watermark data from the reconstructed cover image after applying common geometric transformation attacks (like rotation, cropping, scaling, shearing and deletion of lines or column operation etc.), common enhancement technique attacks (like lowpass filtering, histogram equalization, sharpening, gamma correction, noise addition etc.) and JPEG compression attacks. The proposed scheme is also tested to verify the robustness performance against standard benchmark software "Checkmark" and satisfactory results are achieved against the Checkmark attacks such as Hard and Soft Thresholding, Template Removal, Warping, Dithering, Remodulation and Downsampling/Upsampling etc.

Optimised blind image watermarking method based on firefly algorithm in DWT-QR transform domain

Abstract: Firefly algorithm (FA) is one of the newly developed nature inspired optimisation algorithm, inspired by the flashing behaviour of fireflies that a firefly tends to be attracted towards other fireflies with higher brightness. Thus FA has two advantages: local attractions and automatic regrouping. Based on these good properties, a novel image watermarking method based on FA in discrete wavelet transform (DWT)-QR transform domain is proposed in this study. Structural similarity index measure and bit error rate are used in the objective function to trade-off invisibility and robustness. The experiment results show that the proposed image watermarking method not only meet the need of invisibility, but also has better or comparable robustness as compared with some related methods.

Robust zero-watermarking algorithm based on polar complex exponential transform and logistic mapping

Abstract: This paper introduces a new zero-watermarking algorithm based on polar complex exponential transform (PCET) and logistic mapping. This algorithm takes advantage of the geometric invariance of PCET to improve the robustness of the algorithm against geometric attacks, and the logistic mapping’s sensitivity to initial values to improve the security of the algorithm. First, the algorithm computes the PCET of the original grayscale image. Then it randomly selects PCET coefficients based on logistic mapping, and computes their magnitudes to obtain a binary feature image. Finally, it performs an exclusive-or operation between the binary feature image and the scrambled logo image to obtain the zero-watermark image. At the stage of copyright verification, the image copyright can be determined by performing the exclusive-or operation between the feature image and the verification image and comparing the resulting image to the original logo image. Experimental results show that this algorithm has excellent robustness against geometric attacks and common image processing attacks and better performance compared to other zero-watermarking algorithms.

Software and Hardware FPGA-Based Digital Watermarking and Steganography Approaches: Toward New Methodology for Evaluation and Benchmarking Using Multi-Criteria Decision-Making Techniques

Abstract: Evaluating and benchmarking software and hardware field programmable gate array (FPGA)-based digital watermarking are considered challenging tasks because of multiple and conflicting evaluation criteria. A few evaluation and benchmarking techniques/frameworks have been implemented to digital watermarking or steganography; however, these approaches still present certain limitations. In particular, fixing some attributes on account of other attributes and well-known benchmarking approaches are limited to robust watermarking techniques. Thus, this study aims toward a new methodology for evaluation and benchmarking using multi-criteria analysis for software and hardware “FPGA”-based digital watermarking or steganography. To achieve this objective, two iterations are conducted. The first iteration consists of two stages: discussing software and hardware “FPGA”-based digital watermarking or steganography to create a dataset with various samples for benchmarking and discussing the evaluation method and then disc...

A quality guaranteed robust image watermarking optimization with Artificial Bee Colony

Abstract: Achieving robustness with a limited distortion level is a challenging design problem for watermarking systems in multimedia applications with a guaranteed quality requirement. In this paper, we provide an intelligent system for watermarking through incorporating a meta-heuristic technique along with an embedding method to achieve an optimized performance. The optimization objective is to provide the maximum possible robustness without exceeding a predetermined distortion limit. Hence, the quality level of the watermarking method could be guaranteed through that constraint optimization. A new fitness function is defined to provide the required convergence toward the optimum solution for the defined optimization problem. The fitness function is based on dividing its applied solution population into two groups, where each group is ranked according to a different objective. Thus, the multi-objectives in the problem are decoupled and solved through two single-objective sub-problems. Unlike existing watermarking optimization techniques, the proposed work does not require weighting factors. To illustrate the effectiveness of the proposed approach, we employ a recent watermarking technique, and then use it as the embedding method to be optimized. The Artificial Bee Colony is selected as the meta-heuristic optimization method in which the proposed fitness function is used. Experimental results show that the imposed quality constraint is satisfied, and that the proposed method provides enhanced robustness under different attacks for various quality thresholds. The presented approach offers a robust solution that can be applied to numerous multimedia applications such as film industry, intelligent surveillance and security systems.

Region-based hybrid medical image watermarking for secure telemedicine applications

Abstract: In this paper we propose a novel region based hybrid medical image watermarking (MIW) scheme to ensure authenticity, integrity and confidentiality of medical images. In this scheme a digital medical image is partitioned into region of interest (ROI) and the region of non interest (RONI). To detect and localize ROI tampering with high accuracy pixel wise positional and relational bits are calculated. Positional bit is calculated with respect to MSBs, row and column of the pixel. Relational bit shows the relation between MSBs. Two original LSBs of each ROI pixel are replace by their corresponding positional and relational bits. Original LSBs of ROI pixels are concatenated and embedded in RONI for ROI recovery in the case of tampering. Multiple watermarks i.e. electronic patient record (EPR), hospitals logo and LSBs of ROI are embedded simultaneously as a robust watermark in RONI using IWT-SVD hybrid transform. The proposed scheme is blind and free from false positive detection. Various experiments have been carried out on different medical imaging modalities to evaluate the performance of the proposed scheme in terms of imperceptibility, robustness, tamper detection, localization, recovery and computation time. ROI tampering is detected and recovered with high accuracy. Thus, the proposed scheme is effective in telemedicine applications.

A new digital watermarking evaluation and benchmarking methodology using an external group of evaluators and multi-criteria analysis based on 'large-scale data'

Abstract: Digital watermarking evaluation and benchmarking are challenging tasks because of multiple evaluation and conflicting criteria. A few approaches have been presented to implement digital watermarking evaluation and benchmarking frameworks. However, these approaches still possess a number of limitations, such as fixing several attributes on the account of other attributes. Well-known benchmarking approaches are limited to robust watermarking. Therefore, this paper presents a new methodology for digital watermarking evaluation and benchmarking based on large-scale data by using external evaluators and a group decision making context. Two experiments are performed. In the first experiment, a noise gate-based digital watermarking approach is developed, and the scheme for the noise gate digital watermarking approach is enhanced. Sixty audio samples from different audio styles are tested with two algorithms. A total of 120 samples were evaluated according to three different metrics, namely, quality, payload, and complexity, to generate a set of digital watermarking samples. In the second experiment, the situation in which digital watermarking evaluators have different preferences is discussed. Weight measurement with a decision making solution is required to solve this issue. The analytic hierarchy process is used to measure evaluator preference. In the decision making solution, the technique for order of preference by similarity to the ideal solution with different contexts e.g., individual and group is utilized. Therefore, selecting the proper context with different aggregation operators to benchmark the results of experiment 1 i.e., digital watermarking approaches is recommended. The findings of this research are as follows: 1 group and individual decision making provide the same result in this case study. However, in the case of selection where the priority weights are generated from the evaluators, group decision making is the recommended solution to solve the trade-off reflected in the benchmarking process for digital watermarking approaches. 2 Internal and external aggregations show that the enhanced watermarking approach demonstrates better performance than the original watermarking approach. © 2016 The Authors. Software: Practice and Experience published by John Wiley & Sons Ltd.