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. Accordingly, a DWT-based audio watermarking algorithm robust against the DA/AD conversions is proposed in this paper. To resist the magnitude distortion, the relative energy relationships among different groups of the DWT coefficients in the low-frequency sub-band are utilized in watermark embedding by adaptively controlling the embedding strength. Furthermore, the resynchronization is designed to cope with the linear temporal scaling. The time-frequency localization characteristics of DWT are exploited to save the computational load in the resynchronization. Consequently, the proposed audio watermarking algorithm is robust against the DA/AD conversions, other common audio processing manipulations, and the attacks in StirMark Benchmark for Audio, which has been verified by experiments.
Reversible audio watermarking (RAW) is a promising technique in various applications. To simultaneously meet the demand of achieving high imperceptibility and robustness, this paper proposes a novel RAW scheme based on lattices. The scheme is referred to as Meet-in-the-Middle Embedding (MME), in which the lattice quantization errors are properly scaled and added back to the quantized host signals. Simulations show that MME excels in a wide range of metrics including signal-to-watermark ratio (SWR), objective difference grade (ODG), and bit error rate (BER).
In recent times, communication through the internet has tremendously facilitated the distribution of multimedia data. Although this is indubitably a boon, one of its repercussions is that it has also given impetus to the notorious issue of online music piracy. Unethical attempts can also be made to deliberately alter such copyrighted data and thus, misuse it. Copyright violation by means of unauthorized distribution, as well as unauthorized tampering of copyrighted audio data is an important technological and research issue. Audio watermarking has been proposed as a solution to tackle this iss…
This study aims to present an adaptive audio watermarking method using ideas of wavelet-based entropy (WBE). The method converts low-frequency coefficients of discrete wavelet transform (DWT) into the WBE domain, followed by the calculations of mean values of each audio as well as derivation of some essential properties of WBE. A characteristic curve relating the WBE and DWT coefficients is also presented. The foundation of the embedding process lies on the approximately invariant property demonstrated from the mean of each audio and the characteristic curve. Besides, the quality of the waterm…
Learning to Evade: Adaptive Attacks on Audio Watermarking
University of Missouri-Kansas City（密苏里大学堪萨斯城分校）；University of Hawaii at Manoa（夏威夷大学马诺阿分校）；University of South Florida（南佛罗里达大学）；Michigan State University（密歇根州立大学）；University of Miami（迈阿密大学）
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
University of Houston（德克萨斯大学休斯敦分校）；Waseda University（早稻田大学）；University of Hawaii at Mānoa（夏威夷大学马诺阿分校）；Keio University（庆应大学）；The University of Electro-Communications（电通通信大学）
This work studied embedding positions of digital audio watermarking in wavelet domain, to make beginners understand the nature of watermarking in a short time. Based on the theory of wavelet transform, this paper analyzed statistical distributions of each level after transformation and the features of watermark embedded in different transform levels. Through comparison and analysis, we found that watermark was suitable for embedding into the coefficients of the first four levels of wavelet transform. In current state-of-art approaches, the embedding algorithms were always to replace the coeffi…
University of Science and Technology of China（中国科学技术大学）
As an effective method for intellectual property (IP) protection, model watermarking technology has been applied on a wide variety of deep neural networks (DNN), including speech classification models. However, how to design a black-box watermarking scheme for automatic speech recognition (ASR) models is still an unsolved problem, which is a significant demand for protecting remote ASR Application Programming Interface (API) deployed in cloud servers. Due to conditional independence assumption and label-detection-based evasion attack risk of ASR models, the black-box model watermarking scheme …
MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
Department of Electrical and Computer Engineering, Queen's University, Kingston, ON, Canada（皇后大学电气与计算机工程系）；Department of Electrical and Computer Engineering, University of Waterloo, Waterloo, ON, Canada（滑铁卢大学电气与计算机工程系）
Digital information revolution has brought about many advantages and new issues. The protection of ownership and the prevention of unauthorized manipulation of digital audio, image, and video materials has become an important concern due to the ease of editing and perfect reproduction. Watermarking is identified as a major means to achieve copyright protection. It is a branch of information hiding which is used to hide proprietary information in digital media like photographs, digital music, digital video etc. In this paper, a new image watermarking algorithm that is robust against various att…
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）
In recent years, discrete wavelet transform (DWT) provides an useful platform for digital information hiding and copyright protection. Many DWT-based algorithms for this aim are proposed. The performance of these algorithms is in term of signal-to-noise ratio (SNR) and bit-error-rate (BER) which are used to measure the quality and the robustness of an embedded audio. However, there is a tradeoff relationship between the embedded-audio quality and robustness. The tradeoff relationship is a signal processing problem in the wavelet domain. To solve this problem, this study presents an optimizatio…
Digital watermarking system is a paramount for safeguarding valuable resources and information. Digital watermarks are generally imperceptible to the human eye and ear. Digital watermark can be used in video, audio and digital images for a wide variety of applications such as copy prevention right management, authentication and filtering of internet content. The proposed system is able to protect copyright or owner identification of digital media, such as audio, image, video, or text. The system permutated the watermark and embed the permutated watermark into the wavelet coefficients of the or…
Multimedia security has been the aim point of considerable research activity because of its wide application area. The major technology to achieve copyright protection, content authentication, access control and multimedia security is watermarking which is the process of embedding data into a multimedia element such as image or audio, this embedded data can later be extracted from, or detected in the embedded element for different purposes. In this work, a blind watermarking algorithm based on SVD and circulant matrices has been presented. Every circulant matrix is associated with a matrix for…
Escola Universitària Politècnica de Mataró（马塔罗理工学院）；Dirección General de la Guardia Civil（国民警卫队总局）；Graz University of Technology（格拉茨工业大学）
In this article, the authors discuss the problem of forensic authentication of digital audio recordings. Although forensic audio has been addressed in several articles, the existing approaches are focused on analog magnetic recordings, which are less prevalent because of the large amount of digital recorders available on the market (optical, solid state, hard disks, etc.). An approach based on digital signal processing that consists of spread spectrum techniques for speech watermarking is presented. This approach presents the advantage that the authentication is based on the signal itself rath…
Advancements in deep generative models have made it possible to synthesize images, videos and audio signals that are difficult to distinguish from natural signals, creating opportunities for potential abuse of these capabilities. This motivates the problem of tracking the provenance of signals, i.e., being able to determine the original source of a signal. Watermarking the signal at the time of signal creation is a potential solution, but current techniques are brittle and watermark detection mechanisms can easily be bypassed by applying post-processing transformations (cropping images, shifti…
University of Burgundy（勃艮第大学）；Higher School of Technology（高等技术学院）；Faculty of Sciences, University of Mohammed V（穆罕默德五世大学理学院）
Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to …
In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language content into the target speaker%u2019s fake speech. Then the converted speech generated from VC is post-processed in the time domain to improve the deception ability. The experimental results show that our system has adversarial ability against anti-spoofing detectors with a little compromise in audio quality and speaker similarity. This system ranks top in Track …
