Forensic Watermarking Research Articles

DNN-Based Forensic Watermark Tracking System for Realistic Content Copyright Protection

The metaverse-related content market is active and the demand for immersive content is increasing. However, there is no definition for granting copyrights to the content produced using artificial intelligence and discussions are still ongoing. We expect that the need for copyright protection for immersive content used in the metaverse environment will emerge and that related copyright protection techniques will be required. In this paper, we present the idea of 3D-to-2D watermarking so that content creators can protect the copyright of immersive content available in the metaverse environment. We propose an immersive content copyright protection using a deep neural network (DNN), a neural network composed of multiple hidden layers, and a forensic watermark.

Fast Fallback Watermark Detection Using Perceptual Hashes

Forensic watermarking is often used to enable the tracing of digital pirates that leak copyright-protected videos. However, existing watermarking methods have a limited robustness and may be vulnerable to targeted attacks. Our previous work proposed a fallback detection method that uses secondary watermarks rather than the primary watermarks embedded by existing methods. However, the previously proposed fallback method is slow and requires access to all watermarked videos. This paper proposes to make the fallback watermark detection method faster using perceptual hashes instead of uncompressed secondary watermark signals. These perceptual hashes can be calculated prior to detection, such that the actual detection process is sped up with a factor of approximately 26,000 to 92,000. In this way, the proposed method tackles the main criticism about practical usability of the slow fallback method. The fast detection comes at the cost of a modest decrease in robustness, although the fast fallback detection method can still outperform the existing primary watermark method. In conclusion, the proposed method enables fast and more robust detection of watermarks that were embedded by existing watermarking methods.

Camcording-Resistant Forensic Watermarking Fallback System Using Secondary Watermark Signal

Forensic watermarking is used to track down digital pirates after they illegally redistribute video content. Although existing algorithms often resist common signal processing attacks, they are not always robust against camcording attacks. As a solution in the state of the art, registration methods are used to align the attacked video to the original one. However, watermark detection still fails when the quality is sufficiently decreased or when exposed to targeted attacks. Therefore, this paper proposes a novel fallback system that aims to detect the watermark when traditional methods fail. More concretely, we demonstrate that a primary watermark embedded by a traditional scheme indirectly creates a secondary watermark signal during video encoding. This secondary watermark consists of compression artifacts and is detected by the fallback system. Additionally, the proposed system incorporates video registration to cope with camcording attacks. The experimental results indicate that the fallback system has a striking increase in robustness compared to the existing methods. For example, the observed false-negative rate for targeted attacks improves from 100% to 0%. Moreover, the fallback is camcording resistant even when the traditional method combined with registration is not. In conclusion, the proposed system can be used as a fallback when traditional detection fails.

Rate-Distortion-Preserving Forensic Watermarking Using Quantization Parameter Variation

Watermarking enables the identification of digital pirates that illegally redistribute copyright-protected videos. One of the main challenges is for the watermark to be imperceptible, while not increasing the video bit rate. Additionally, the system should be robust to attacks that attempt to remove the watermark. Therefore, this paper proposes a robust watermarking technique that does not degrade the video quality nor negatively affect the video bit rate. In other words, it preserves the video encoder’s compression efficiency or rate-distortion performance. For watermark embedding, the quantization parameters are varied during video compression. As a result, different compression artifacts are introduced, although they do not distort the video more than those that occur during ordinary video compression. The collection of artifacts represents the watermark and is used for watermark detection. The experimental results prove that the proposed approach retains the rate-distortion performance better than state-of-the-art techniques. Furthermore, the watermarks are robust to recompression and noise attacks. In conclusion, the proposed method enables content providers to perform forensic watermarking without affecting the compression efficiency.

High Performance and Energy Efficient Image Watermarking for Video Using a Mobile Device

This article describes the basic information hiding technique that is most commonly used nowadays. As evolution in the communication media has made information access much easier but has also increased the risks of invading privacy and ownership. To overcome such threats, watermarking is one of the most suitable methods used for hiding information. It is the process of inserting audio, video, image or text for owner verification. A study on spatial and temporal domain watermarking is conducted. An experiment is carried out for the analysis of power and time consumption while inserting and extraction of the watermarks. For better understanding of the concept, embedding of an image on a video was performed using a computer and a mobile with similar logic. This concluded that the watermarking process can be implemented by both computer and mobile phones. Extraction of image was done with PSNR value that was inserted on a video. Only limitation found in this process was tracing back to the source of content theft and that is covered by forensic watermarking.

The business and technical challenges of forensic watermarking for ultra-high definition

The advent of ultra-high definition content requires a new generation of content protection that mandates the use of forensic watermarking. For two decades, watermarking has evolved and matured. This paper explores how to implement forensic watermarking successfully. It presents the different possible architectures, one-step versus two-step, client side versus server side, and analyses their respective advantages and drawbacks. This paper studies whether forensic watermarking can be compliant with privacy. Furthermore, this paper addresses the issue of non-repudiability that is often forgotten during design.

안드로이드 플랫폼에서 odex 파일을 이용한 불법 복제 앱 탐지 방법

모바일 환경의 변화에 따라 안드로이드 앱의 사용이 증가하면서 앱에 대한 관심도 증가하였다. 하지만 불법으로 복제된 앱의 사용도 증가하여 앱 마켓의 투명성과 신뢰성이 저하되고 앱 개발자의 저작권을 침해하는 피해 사례가 발생하고 있다. 불법으로 복제된 앱의 사용을 방지하는 다양한 기술이 연구되었지만, 이를 우회하는 방법이 있기도 하고 또한 최초 유포자에 대한 정보를 알아낼 수 없어서 법적으로 제재하기도 어렵다. 본 논문에서는 안드로이드 플랫폼에서 불법 복제 앱을 탐지하는 방법을 제안한다. 불법 복제 앱 탐지기는 앱 설치 과정에서 생성되는 odex 파일을 사용함으로 불법 복제 앱을 탐지하고, 포렌식 워터마크 기술을 사용함으로써 최초 유포자의 정보를 알아낼 수 있다. 제안하는 불법 복제 앱 탐지기는 시스템 서버에서 서비스 형태로 실행되어 사용자에게 노출되지 않는다. 실험 결과, 불법 복제 앱 탐지기는 평균 0.2초 이내로 불법 복제 앱을 탐지하고 삭제하는 것이 가능하다. According to the changes of the mobile environments, the usage and interest of the Android apps have been increased. But the usage of illegally-copied apps has been also increased. And the transparency and dependability of the app markets has been decreased. Therefore there are many cases for the copyright infringement of app developers. Although several methods for preventing illegally-copied apps have been studied, there may exist possible ways to bypass the methods. Since it is difficult to find out the first distributors of the illegally-copied apps, it is not easy to punish them legally. This paper proposes the method of detecting illegally-copied apps. The proposed detector can detect the illegally-copied apps using odex file, which is created when the app is installed. The detector can also find out the information of the first distributors based on forensic watermark technique. Since the illegally-copied app detector is running as a service on the system server, it is granted that the detector hides from the users. As an experiment result, the illegally-copied app detector takes on average within 0.2 seconds to detect and delete an illegally-copied app.

Toward Real-Time Detection of Forensic Watermarks to Combat Piracy by Live Streaming

Over the past several years, antipiracy analysts have documented the transition of casual content piracy away from Torrent networks to streaming sites that provide immediate access to not only live television (TV) broadcasts, but also file-based pirated content, such as movies and TV episodes. Because live content such as professional sports or pay-per-view events have only one release window, they will lose market value immediately if they can be streamed live, thus there is a recognized need to act quickly in the case of piracy and hence to shorten the time needed to extract the forensic watermark payload to as close to realtime as possible. In working toward inline detection of forensic watermarks from streaming content, we seek to enable a new tool designed to identify the pirate source in minutes. With the ability to detect a session-based forensic watermark directly from a video stream, it is possible for an operator to disable a set-top box or streaming client while the transmission is still in progress.

False Negative probabilities in Tardos codes

Forensic watermarking is the application of digital watermarks for the purpose of tracing unauthorized redistribution of content. One of the most powerful types of attack on watermarks is the collusion attack, in which multiple users compare their differently watermarked versions of the same content. Collusion-resistant codes have been developed against these attacks. One of the most famous such codes is the Tardos code. It has the asymptotically optimal property that it can resist \(c\) attackers with a code of length proportional to \(c^2\). Determining error rates for the Tardos code and its various extensions and generalizations turns out to be a nontrivial problem. In recent work we developed an approach called the convolution and series expansion (CSE) method to accurately compute false positive accusation probabilities. In this paper we extend the CSE method in order to make it possible to compute a bound on the False Negative accusation probabilities.

Anti-Piracy for movies using Forensic Watermarking

In the past decade internet worked perfectly with distribution of the digital data for pictures, music and videos. Although digital data have many advantages over analogue data, the rightful ownership of the digital data source is at of risk. The copyright protection for digital media becomes an important issue of piracy. Watermarking is a very important field for copyrights of various electronic documents and multimedia. This paper presents a digital forensic watermarking method for authorization against copying or piracy of digital video. The core idea is to use biometric generated keys in the embedding process of watermark. The host video is first randomized by Heisenberg decomposition and Discrete Fourier Transform (DFT). The invisible watermark is embedded in the I-frame of the host video. The watermarks are embedded in the least significant bit (LSB) of the each block. The forensic watermark provides “The Chain of Custody” throughout the life cycle of the video distribution. The experimental result of test sequence demonstrates that the proposed work gives high security and robustness. General Terms Algorithms, Security, Watermarking.

Bandwidth efficient buyer-seller watermarking protocol

Digital watermarking has been used widely for the purposes of copyright protection and copy deterrence for multimedia content. In a forensic watermarking architecture, a buyer-seller watermarking protocol can enable a seller to identify a traitor from a pirated copy, while preventing the seller from framing an innocent buyer. Existing schemes are inefficient in practice for their high bandwidth usage. This paper proposes a buyer-seller watermarking protocol that is efficient from the bandwidth usage point of view. First, multicast that is an efficient transport technology for one-to-many communication is exploited, which can reduce the bandwidth usage significantly. Second, symmetric encryption instead of public-key encryption is performed on the multimedia content, which also can reduce the complexity and communication cost.

A novel semi-fragile forensic watermarking scheme for remote sensing images

A semi-fragile watermarking scheme for multiple band images is presented. We propose to embed a mark into remote-sensing images applying a tree-structured vector quantization approach to the pixel signatures, instead of processing each band separately. The signature of the multi- or hyperspectral image is used to embed the mark into it in order to detect any significant modification of the original image. The image is segmented into three-dimensional blocks and a tree-structured vector quantizer (TSVQ) is built for each block. These trees are manipulated using an iterative algorithm until the resulting block satisfies a required criterion which establishes the embedded mark. The method is shown to be able to preserve the mark under lossy compression (above a given threshold) but, at the same time, it detects possibly forged blocks and their position in the whole image.

A Buyer–Seller Watermarking Protocol Based on Secure Embedding

In a forensic watermarking architecture, a buyer-seller protocol protects the watermark secrets from the buyer and prevents false infringement accusations by the seller. Existing protocols encrypt the watermark and the content with a homomorphic public-key cipher and perform embedding under encryption. When used for multimedia data, these protocols create a large computation and bandwidth overhead. In this correspondence, we show that the same functionality can be achieved efficiently using recently proposed secure watermark embedding algorithms.

Decode-Time Forensic Watermarking of AAC Bitstreams

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> In digital rights-management systems, forensic watermarking complements encryption and deters the capture and unauthorized redistribution of the rendered content. In this paper, we propose a novel watermarking method which is integrated into the advanced audio coding (AAC) standard's decoding process. For predefined frequency bands, the method intercepts and modifies the scale factors, which are utilized for dequantization of spectral coefficients. It thereby modulates the short-time envelope of the bandlimited audio and embeds a watermark which is robust to various attacks, such as capture with a microphone and recompression at lower bit rates. Inclusion of watermark embedding in the AAC decoder has practically no effect on the decoding complexity. As a result, the proposed method can be integrated even into resource-constrained devices, such as portable players without any additional hardware. </para>

Electronic content delivery and forensic watermarking

Today, digital content distribution is already common practice for media types like audio. It is expected that in the near future, systems like Video-on-Demand will also increase in popularity. Many Digital Right Management (DRM) models exist enforcing the copyrights associated with the distributed content. We argue that a simplified model based on so-called forensic watermarks is a viable alternative approach that closely mimics the current model of physical music and video distribution by providing a reasonable compromise between the conflicting interests of consumers and content owners. In this paper, we address the forensic watermark DRM model and introduce a generalized architecture for the distribution server and the forensic watermark tracker. In this model, important attack scenarios are identified as being the `copy attack' and the watermark `rendering'. We show that it is more difficult to successfully work out these attack scenarios by (i) integrating a content identification and watermarking system and (ii) making the watermark (both the carrier signal as well as the payload) content dependent. In addition to these security aspects, we also focus on efficiency of the distribution server. By separating the computational efforts in so-called pre-coding and on-line computational phases, the required signal processing resources of the distribution server can be reduced significantly. The general architecture including security and efficiency requirements are analyzed in a practical example of Electronic Music Delivery (EMD). We show that computational complexity can be reduced up to a factor 4 compared to a straightforward approach. In practice, it means that with current state-of-the art computers (Pentium IV, 1 GHz) watermark embedding speeds of about 40 times Real Time (RT) can be achieved. In addition to the embedding architecture, we also demonstrate an efficient method for detecting watermarks in a forensic watermark tracker. Having multimedia identification fingerprints available (required for working with content-dependent watermarks), the efficiency of watermark detection can be enhanced by using them as side information. Again, in our EMD prototype, we demonstrate that (depending on the parameter settings) the detector can run up to 50 times faster than a blind detector, in which the original or the fingerprint is not available.