Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based methods achieved impressive results in both visual quality and message payload under a wide variety of image distortions. However, these methods all require differentiable models for the image distortions at training time, and may generalize poorly to unknown distortions. This is undesirable since the types of distortions applied to watermarked images are usually unknown and non-differentiable. In this paper, we propose a new framework for distortion-agnostic watermarking, where the image distortion is not explicitly modeled during training. Instead, the robustness of our system comes from two sources: adversarial training and channel coding. Compared to training on a fixed set of distortions and noise levels, our method achieves comparable or better results on distortions available during training, and better performance on unknown distortions.
Video watermarking embeds a message into a cover video in an imperceptible manner, which can be retrieved even if the video undergoes certain modifications or distortions. Traditional watermarking methods are often manually designed for particular types of distortions and thus cannot simultaneously handle a broad spectrum of distortions. To this end, we propose a robust deep learning-based solution for video watermarking that is end-to-end trainable. Our model consists of a novel multiscale design where the watermarks are distributed across multiple spatial-temporal scales. It gains robustness…
In this work, we present an efficient multi-bit deep image watermarking method that is cover-agnostic yet also robust to geometric distortions such as translation and scaling as well as other distortions such as JPEG compression and noise. Our design consists of a light-weight watermark encoder jointly trained with a deep neural network based decoder. Such a design allows us to retain the efficiency of the encoder while fully utilizing the power of a deep neural network. Moreover, the watermark encoder is independent of the image content, allowing users to pre-generate the watermarks for furth…
As an efficient watermark attack method, geometric distortions destroy the synchronization between watermark encoder and decoder. And the local geometric distortion is a famous challenge in the watermark field. Although a lot of geometric distortions resilient watermarking schemes have been proposed, few of them perform well against local geometric distortion like random bending attack (RBA). To address this problem, this paper proposes a novel watermark synchronization process and the corresponding watermarking scheme. In our scheme, the watermark bits are represented by random patterns. The …
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Shenzhen Key Laboratory of Intelligent Media and Content Understanding（深圳市智能媒体与内容理解重点实验室）；Tencent AI Lab（腾讯人工智能实验室）
Department of Computer Science University of Nebraska Omaha（内布拉斯加大学奥马哈分校计算机科学系）
This paper presents a deep learning-based audio-in-image watermarking scheme. Audio-in-image watermarking is the process of covertly embedding and extracting audio watermarks on a cover-image. Using audio watermarks can open up possibilities for different downstream applications. For the purpose of implementing an audio-in-image watermarking that adapts to the demands of increasingly diverse situations, a neural network architecture is designed to automatically learn the watermarking process in an unsupervised manner. In addition, a similarity network is developed to recognize the audio waterm…
Audio watermarking has played an important role in multimedia security. In many applications using audio watermarking, D/A and A/D conversions (denoted by DA/AD in this paper) are often involved. In previous works, however, the robustness issue of audio watermarking against the DA/AD conversions has not drawn sufficient attention yet. In our extensive investigation, it has been found that the degradation of a watermarked audio signal caused by the DA/AD conversions manifests itself mainly in terms of wave magnitude distortion and linear temporal scaling, making the watermark extraction failed.…
We propose a novel audio watermarking system that is robust to the distortion due to the indoor acoustic propagation channel between the loudspeaker and the receiving microphone. The system utilizes a set of new algorithms that effectively mitigate the impact of room reverberation and interfering sound sources without using dereverberation procedures. The decoder has low-latency and it operates asynchronously, which alleviates the need for explicit synchronization with the encoder. It is also robust to standard audio processing operations in legacy watermarking systems, e.g., compression and v…
Growth of the Internet and networked multimedia systems has emphasized the need for copyright protection of the media. Media can be images, audio clips, videos and etc. Digital watermarking is today extensively used for many applications such as authentication of ownership or identification of illegal copies. Digital watermark is an invisible or maybe visible structure added to the original media (known as asset). Images are considered as communication channel when they are subject to a watermark embedding procedure so in the case of embedding a digital watermark in an image, the capacity of t…
The availability of bandwidth for internet access is sufficient enough to communicate digital assets. These digital assets are subjected to various types of threats. [19] As a result of this, protection mechanism required for the protection of digital assets is of priority in research. The threat of current focus is unauthorized copying of digital assets which give boost to piracy. This under the copyright act is illegal and a robust mechanism is required to curb this kind of unauthorized copy. To safeguard the copyright digital assets, a robust digital watermarking technique is needed. The ex…
University of Science and Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云人工智能）；City University of Hong Kong（香港城市大学）
Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However, these valuable deep models are exposed to a huge risk of infringements. For example, if the attacker has the full information of one target model including the network structure and weights, the model can be easily finetuned on new datasets. Even if the attacker can only access the output of the target model, he/she can still train another similar surrogate…
Multiple watermarking technique, embedding several watermarks in one carrier, has enabled many interesting applications. In this study, a novel multiple watermarking algorithm is proposed based on the spirit of spread transform dither modulation (STDM). It can embed multiple watermarks into the same region and the same transform domain of one image; meanwhile, the embedded watermarks can be extracted independently and blindly in the detector without any interference. Furthermore, to improve the fidelity of the watermarked image, the properties of the dither modulation quantizer and the propose…
TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity
Anhui Province Key Laboratory of Digital Security, University of Science and Technology of China（安徽省数字安全重点实验室，中国科学技术大学）；School of Computing, National University of Singapore（computing学院，新加坡国立大学）
Watermarking helps in ensuring originality, ownership and copyrights of a digital image. This paper aims at embedding a Watermark in an image using Wave Atom Transform. Preference of Wave Atoms on other transformations has been due to its sparser expansion, adaptability to the direction of local pattern, and sharp frequency localization. In this scheme, we had tried to spread the watermark in an image so that the information at one place is very small and undetectable. In order to extract the watermark and verify ownership of an image, one would have the advantage of prior knowledge of embedde…
Wroclaw University of Science and Technology（弗罗茨瓦夫理工大学）；Vestigit
In this paper we present a novel deep framework for a watermarking - a technique of embedding a transparent message into an image in a way that allows retrieving the message from a (perturbed) copy, so that copyright infringement can be tracked. For this technique, it is essential to extract the information from the image even after imposing some digital processing operations on it. Our framework outperforms recent methods in the context of robustness against not only spectrum of attacks (e.g. rotation, resizing, Gaussian smoothing) but also against compression, especially JPEG. The bit accura…
Reversible visible watermarking (RVW) is an active copyright protection mechanism. It not only transparently superimposes copyright patterns on specific positions of digital images or video frames to declare the copyright ownership information, but also completely erases the visible watermark image and thus enables restoring the original host image without any distortion. However, existing RVW algorithms mostly construct the reversible mapping mechanism for a specific visible watermarking scheme, which is not versatile. Hence, we propose a generic RVW framework to accommodate various visible w…
Watermarking is an operation of embedding an information into an image in a way that allows to identify ownership of the image despite applying some distortions on it. In this paper, we presented a novel end-to-end solution for embedding and recovering the watermark in the digital image using convolutional neural networks. The method is based on spreading the message over the spatial domain of the image, hence reducing the "local bits per pixel" capacity. To obtain the model we used adversarial training and applied noiser layers between the encoder and the decoder. Moreover, we broadened the s…
Insertion of a text message, audio data or/and an image into another image or 3D model is called as a watermarking process. Watermarking has variety of applications like: Copyright Protection, Owner Identification, Copy Protection and Data Hiding etc., depending upon the type of watermark insertion algorithm. Watermark remains in the content after applying various attacks without any distortions. The blind watermarking method used in the system is based on a wavelet transform, a fuzzy inference system and a multi-resolution representation (MRR) of the 3d model. The watermark scrambled by Arnol…
Nowadays, with the development of public network usage, medical information is transmitted throughout the hospitals. The watermarking system can help for the confidentiality of medical information distributed over the internet. In medical images, regions-of-interest (ROI) contain diagnostic information. The watermark should be embedded only into non-regions-of-interest (NROI) to keep diagnostic information without distortion. Recently, ROI based watermarking has attracted the attention of the medical research community. The ROI map can be used as an embedding key for improving confidentiality …
With recent advances in machine learning, researchers are now able to solve traditional problems with new solutions. In the area of digital watermarking, deep-learning-based watermarking technique is being extensively studied. Most existing approaches adopt a similar encoder-driven scheme which we name END (Encoder-NoiseLayer-Decoder) architecture. In this paper, we revamp the architecture and creatively design a decoder-driven watermarking network dubbed De-END which greatly outperforms the existing END-based methods. The motivation for designing De-END originated from the potential drawback …
