Zero-knowledge Proof (ZKP) allows active image authentication to prove image integrity after editing without revealing its source. However, existing ZKP solutions require impractical execution time, leaving a considerable gap between theory and practice. To tackle this, we present a Region-Aware Photo Assurance System based on the nature of image editing with privacy: sensitive information is usually local and relatively small, and thus by cropping and/or adding mosaic to these small regions suffices to protect privacy. Using ZKP for the locally edited region and digital signature for the others can still ensure the integrity of an image, with significantly better efficiency. We comprehensively analyzed the system's performance and showed the advantage of our system compared with the state-of-the-art ZKP-based method, PhotoProof, with 15x/60xfaster on the KeyGen/Proof operations and 25x lower in the Proof size. Furthermore, we protect several real-world images selected in the Redaction dataset with our system. Our system achieves up to 2,700x faster than PhotoProof for a proof generation. We expect the system can become a practical system for real-world applications.
Digital Media Forensic Detection
Advanced Steganography and Watermarking Techniques
Frederik Temmermans, Sabrina Caldwell, Symeon Papadopoulos, Fernando Pereira · 5 authors
Advances in media content manipulation and artificially generated content pose new challenges to the assessment of media authenticity. While automated detection methods can provide meaningful insights and decision support in some scenarios, they cannot provide trustworthy and comprehensive information about the origin and provenance of media assets. Therefore, a longer-term approach should rather focus on secure and interoperable annotations related to the creation and provenance of media. In October 2020, the JPEG Committee initiated a standardization exploration named "JPEG Fake Media" to address these needs. Subsequently, since many of the requirements, for example related to secure annotation and identification of media assets, are also relevant to achieve interoperability in Non-Fungible Tokens (NFTs) an additional exploration was initiated, specifically focused on standardization needs for NFTs. In April 2022 a first Call for Proposals on JPEG Fake Media was issued. Based on the responses to the call, a new standardization project named JPEG Trust was initiated to specify an interoperable framework for establishing trust in media production, distribution, and consumption. This paper presents the journey of JPEG to leverage formal methods of standardization in this context, starting from the initial JPEG Fake Media exploration, followed by the subsequent consideration of NFT use cases and requirements, through to the commencement of the new JPEG Trust international standard.
Open access
2 source records
Digital Media Forensic Detection
Advanced Steganography and Watermarking Techniques
A generative adversarial network is a deep learning model, an unsupervised learning method. In computer vision, the generative adversarial network is a research direction with rapid development in recent years; Similarly, the rise of cryptocurrency Non-Fungible Tokens (NFT) in recent years has also attracted much attention to the field of art. As an "irreplaceable currency" NFT provides a more novel and convenient way for content creators and artists to create and increases the continuous income of original creators. At the same time, it has also attracted widespread attention to the financial field. Therefore, this paper is determined to combine the generative adversarial network of the production of NFT and discuss and analyze the autonomous computer generation of artworks. Firstly, this paper starts with the model's structure, the design of the objective function, Block chain technology, and Irreplaceable tokens encrypted using blockchain technology. Then, the image generated by the whole generative adversarial network and transformed into NFT works are described in detail. In addition, this paper briefly discusses the development ethics of human art and machine art and the prospects for its development trend.
Open access
Generative Adversarial Networks and Image Synthesis
Blockchain technology is used to support digital assets such as cryptocurrencies and tokens. Commonly, smart contracts are used to generate tokens on top of the blockchain network. There are two fundamental types of tokens: fungible and non-fungible (NFTs). This paper focuses on NFTs and offers a technique to spot plagiarism in NFT images. NFTs are information that is appended to files to produce distinctive signatures. It can be found in image files, real artifacts, literature published online, and various other digital media. Plagiarism and fraudulent NFT images are becoming a big concern for artists and customers. This paper proposes an efficient deep learning-based approach for NFT image plagiarism detection using the EfficientNet-B0 architecture and the Triplet Semi-Hard Loss function. We trained our model using a dataset of NFT images and evaluated its performance using several metrics, including loss and accuracy. The results showed that the EfficientNet-B0-based deep neural network with triplet semi-hard loss outperformed other models such as Resnet50, DenseNet, and MobileNetV2 in detecting plagiarized NFTs. The experimental results demonstrate sufficient to be implemented in various NFT marketplaces.
Open access
Digital Media Forensic Detection
Generative Adversarial Networks and Image Synthesis
Advanced Steganography and Watermarking Techniques
There has been a lot of hype around blockchains and non fungible tokens (NFTs). However the technology is yet to establish itself beyond a limited number of fairly specific use cases, namely cryptocurrency and digital art. This commentary seeks to propose an outline framework for NFTs and Blockchains for digital provenance of important digital artifacts such as citizen intelligence and newspapers. This article develops an outline framework and reasoning for NFT and Blockchain technology to be used to establish provenance of digital artifacts in what is an increasingly contested digital space. A space where the subtle (and perhaps not so subtle) manipulation of video, images, and all forms of digital evidence and documents by humans, and increasingly artificial intelligence, could be used to challenge contemporary narratives and manipulate the past. This framework should be seen as an opening proposal to ignite discussion, as the establishment of any technology in this space should not be done without careful consideration. Nor should it be done by a single individual or group.
With the growing popularity of smartphone photography in recent years, web photos play an increasingly important role in all walks of life. Source camera identification of web photos aims to establish a reliable linkage from the captured images to their source cameras, and has a broad range of applications, such as image copyright protection, user authentication, investigated evidence verification, etc. This paper presents an innovative and practical source identification framework that employs neural-network enhanced sensor pattern noise to trace back web photos efficiently while ensuring security. Our proposed framework consists of three main stages: initial device fingerprint registration, fingerprint extraction and cryptographic connection establishment while taking photos, and connection verification between photos and source devices. By incorporating metric learning and frequency consistency into the deep network design, our proposed fingerprint extraction algorithm achieves state-of-the-art performance on modern smartphone photos for reliable source identification. Meanwhile, we also propose several optimization sub-modules to prevent fingerprint leakage and improve accuracy and efficiency. Finally for practical system design, two cryptographic schemes are introduced to reliably identify the correlation between registered fingerprint and verified photo fingerprint, i.e. fuzzy extractor and zero-knowledge proof (ZKP). The codes for fingerprint extraction network and benchmark dataset with modern smartphone cameras photos are all publicly available at https://github.com/PhotoNecf/PhotoNecf 1.
Open access
3 source records
cs.CV
Digital Media Forensic Detection
Advanced Steganography and Watermarking Techniques
Preventive measures to stop copyright infringement are yet to be implemented on current decentralized music-sharing platforms. There is no mechanism to reject modified audio before they go online, so some decentralized music platforms become places full of pirated audio files. To address this problem, a perceptual hash-based audio detection method for copyright protection in decentralized music sharing was proposed. Chromaprint, an open-source audio fingerprint program, generates a hash value to detect copyright infringement. To assess the perceptual hash technique’s robustness, Chromaprint generates a hash value from an audio file that can be modified with several signal processing attacks. The results of the detection system show that Chromaprint is very effective at spotting copyright infringement, with an average match rate of 92.64%. Deployed using a public Ethereum blockchain test network, the execution time from hashing to uploading to the IPFS distributed storage is only 616.3 ms.
Advanced Steganography and Watermarking Techniques
Cryptocurrencies have become a global phenomenon and its trading volume has been increasing since 2017 Aloosh and Li (2019). However, cryptocurrencies have been accused of market manipulation in the past. Benford’s law is widely used for detecting probability of frauds and manipulation in various fields. This study applied Benford’s law on trade volume of cryptocurrencies. Chi- square statistics revealed that except for Cardano and USDT all the other cryptocurrencies did not conform to the distribution and reveals the dataset could have been manipulated. This method may be used as the pre-requisite before doing fine-grain screening such as machine learning and graph-based searching.
Blockchain can change how media content dispersion, utilization, and installment for music, video, and different means occur. Modified multi-content assistance bundles are past the abilities of current frameworks. Overseeing advanced privileges, eminence assortments, and exchanges among different go-betweens is very troublesome in the present computerized environments. By bringing responsibility, security, and control to the media inventory network, blockchain, with its common record approach, will assist with improving the media production network and diminish copyright encroachments. It may, for instance, decrease copyright encroachments in music streaming, where distributors and lyricists much of the time denounce music web-based features like Spotify, Napster, and Pandora of not paying them anything they are owed, losing up to 25% of streaming eminences.
Blockchain Technology Applications and Security
Advanced Steganography and Watermarking Techniques
With the recent proliferation of blockchains, identifying security risks to them has become an important issue. Among the various types of cyberattacks against blockchains, the blockchain poisoning attack involves the storing of malicious data in the blockchain to compromise it. One scenario is an attack that distributes forgeries of digital content traded and managed using Non-Fungible Token (NFT) on the blockchain. Currently, concomitant with the growing interest in NFT-based content trading, blockchain poisoning attacks on NFT trading and their effects have also increased. In this study, we examined the issues that may lead to attacks in the process from generation to distribution of digital content using NFT from the viewpoint of flexibility and interoperability of the content. Consequently, we discovered that there are two types of attack risks in NFT trading using malicious content: fake attacks and reuse attacks. As a countermeasure against these attacks, we propose a method for verifying the authenticity of the content itself using a decentralized scheme. The proposed method ensures the confidentiality of contents by using deep learning as an irreversible transformation operation in the distributed scheme and for privacy protection.
Open access
Advanced Steganography and Watermarking Techniques
Wei Yao, Jingyi Gu, Wenlu Du, Fadi P. Deek · 5 authors
The increasing popularity of crypto assets has resulted in greater cryptocurrency investor interest and more exposure in both industry and academia. Despite the substantial socioeconomic benefits, the anonymous character of cryptocurrency trading makes it prone to abuse and a magnet for illicit purposes, which cause monetary losses for individual traders and erosion in the standing of the tokenomics industry. To regulate the illicit behavior and secure users' privacy for cryptocurrency trading, we present an Anomaly Detection and Privacy-Preserving (ADPP) Framework integrating blockchain and deep learning technologies. Specifically, ADPP leverages blockchain technologies to build a user management platform that ensures anonymity and enhances the privacy-preservation of user information. Atop the user management system, an Anomaly Detection System adapts neural networks and imbalanced learning on topological cryptocurrency flow among users to identify anomalous addresses and maintain a sanction list repository. The experiments on the real-world dataset demonstrate the effectiveness and superior performance of ADPP. The flexible framework can be easily generalized to the crypto assets with public real-time transaction (e.g., Non-fungible Token), which takes up a significant proportion of market capitalization in the domain of tokenomics.
With the significant advancement in digital photo and video editing software, it is becoming very easy to modify digital video content. However, because of the increased misuse of such editing software, detecting the modification of digital content and verifying the authenticity of such content has become a significant challenge. The paper aims to address the main problem of tampering with digital video content by verifying that digital video received via digital media is tamper-free and identical to what was sent. To solve and control such a problem, blockchain features are used by creating a decentralized application on the Ethereum platform. A watermark is also used to access the data stored on the blockchain. Blockchain-based digital video content authentication technology is safe and reliable, with lower recording time and lower cost. Since the process of watermark embedding occurs only for the first and last frame, the content of the digital video does not change and, as a result, the PSNR value of the video is unaffected. This system allows a user receiving digital video to verify the authenticity of the content received without referring to the sender.
Advanced Steganography and Watermarking Techniques
The recent creation of Non Fungible Tokens (NFTs) has enabled a multibillionaire market for digital artistic works including images or sequence of images, videos, and animated gifs. With this new trend issues regarding fraud, stolen works, authenticity, and copyright came along. The goal of this chapter is to provide an overview of the watermarking techniques that can be employed to mitigate those issues. We will discuss transparency, robustness, and payload of watermarking techniques aiming to educate the artists, researchers, and developers about the many approaches that watermarking techniques provide and the resulting trade-offs. We focus on fragile watermarking techniques due to their high transparency for embedding into artistic works. We discuss the spread spectrum and Least Significant Bit techniques. We describe the usual process of NFT minting into a blockchain and propose a more secure certification protocol with watermarking which employs the same usual NFT minting offered by current marketplaces. The proposed certification protocol mints a checksum string into a blockchain, ensuring the validity of the watermark and the information embedded into this watermark. This proposed protocol validates the date of creation and author identification which are transparently embedded in the artistic work, thus, increasing the security and confidence of markets for artistic works transactions.
Open access
Advanced Steganography and Watermarking Techniques
The data in the blockchain cannot be tampered with and the users are anonymous, which enables the blockchain to be a natural carrier for covert communication. However, the existing methods of covert communication in blockchain suffer from the predefined channel structure, the capacity of a single transaction is not high, and the fixed transaction behaviors will lower the concealment of the communication channel. Therefore, this paper proposes a derivation matrix-based covert communication method in blockchain. It uses dual-key to derive two types of blockchain addresses and then constructs an address matrix by dividing addresses into multiple layers to make full use of the redundancy of addresses. Subsequently, to solve the problem of the lack of concealment caused by the fixed transaction behaviors, divide the rectangular matrix into square blocks with overlapping regions and then encrypt different blocks sequentially to make the transaction behaviors of the channel addresses match better with those of the real addresses. Further, the linear congruence algorithm is used to generate random sequence, which provides a random order for blocks encryption, and thus enhances the security of the encryption algorithm. Experimental results show that this method can effectively reduce the abnormal transaction behaviors of addresses while ensuring the channel transmission efficiency.
Open access
Advanced Steganography and Watermarking Techniques
Daniel Kang, Tatsunori Hashimoto, Ion Stoica, Yi Sun
Over the past few years, AI methods of generating images have been increasing in capabilities, with recent breakthroughs enabling high-resolution, photorealistic "deepfakes" (artificially generated images with the purpose of misinformation or harm). The rise of deepfakes has potential for social disruption. Recent work has proposed using ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge) and attested cameras to verify that images were taken by a camera. ZK-SNARKs allow verification of image transformations non-interactively (i.e., post-hoc) with only standard cryptographic hardness assumptions. Unfortunately, this work does not preserve input privacy, is impractically slow (working only on 128$\times$128 images), and/or requires custom cryptographic arguments. To address these issues, we present zk-img, a library for attesting to image transformations while hiding the pre-transformed image. zk-img allows application developers to specify high level image transformations. Then, zk-img will transparently compile these specifications to ZK-SNARKs. To hide the input or output images, zk-img will compute the hash of the images inside the ZK-SNARK. We further propose methods of chaining image transformations securely and privately, which allows for arbitrarily many transformations. By combining these optimizations, zk-img is the first system to be able to transform HD images on commodity hardware, securely and privately.
Open access
2 source records
Digital Media Forensic Detection
Adversarial Robustness in Machine Learning
Generative Adversarial Networks and Image Synthesis
Ke Yang, Da Li, Qinglei Guo, Hejian Wang · 6 authors
With the acceleration of the digital transformation of the power system, the electronic data in the power production operation has shown an explosive growth. However, the increasing proliferation of deep forgery technology has brought huge hidden dangers to the electronic data management of power grid enterprises, and it is urgent to build a trusted management system for electronic data. This paper proposes a blockchain-based deep forgery data identification and traceability framework. Firstly, a method of trusted identification of electronic data based on blockchain is proposed, which constructs the unique identification of data and embeds it in the electronic data as a digital watermark. Second, introduce blockchain-based electronic data forensic appraisal technology to conduct authenticity and similarity analysis of electronic data. Finally, a deep forgery data traceability mechanism based on digital identification is designed to realize deep forgery data traceability and dissemination supervision. After comparative analysis, the framework is more secure and efficient in deep forgery data supervision, and can provide key support for building a trusted content system in cyberspace.
In recent years the use of images in communication has significantly increased. It is important to secure images from unauthorized access and manipulation. Copyright protection approaches protect data from attacks that result in modification, illegal copying or removal. Our proposed approach uses watermarking and blockchain to confirm authentication. Watermarking is a data-hiding technique whereby data is hidden inside an image to make it difficult to modify. Blockchain at its core, is a distributed-ledger that stores secured and encrypted information while ensuring that it is not changed by someone. We present an imperceptible and secure watermarking approach for digital images using the discrete wavelet transform (DWT). The encrypted watermark is saved in the blockchain. When an image is received and it is to be authenticated, the watermark is retrieved from the blockchain and compared with the watermark that is extracted from the given image. The visual quality of the proposed watermarking approach is tested by comparing the original and watermarked images using peak signal-to-noise ratio (PSNR). The basic challenge that we face is finding suitable locations for inserting the watermark while satisfying the imperceptibility aspects along with the security of the algorithm to reach its highest effectiveness.
Advanced Steganography and Watermarking Techniques
Sarah Khadijah Taylor, Steve Ho-yong Kim, Khairul Akram Zainol Ariffin, Siti Norul Huda Sheikh Abdullah
Studies have shown that the existing methodology of digital forensics preservation, which is to acquire and hash the evidence, is insufficient for cryptocurrencies as it does not secure the value. To address this issue, investigators secure the cryptocurrency by transferring it to a crypto wallet controlled by the Law Enforcement Agencies(LEAs). This process will unavoidably modify some data. Despite the criticality of this issue, inadequate studies have been made in this area. In addition, current guidelines on securing the cryptocurrency lack a comprehensive description from the perspective of digital evidence preservation principles. Crucial data to be documented throughout the preservation process were also not properly listed. Therefore, this study aims to address the gap in preserving cryptocurrencies from crypto wallets. Three objectives were then laid out; (1) to develop a methodology that is mapped comprehensively with digital evidence preservation principle, (2) to describe and provide justification on the inevitably modified data, and (3) to list crucial data to be documented during preservation process. The methods to achieve the objectives were critical examinations on various types of crypto wallets and by using simulation. The result shows that the study is able to provide a comprehensive crypto wallets preservation methodology to forensic investigators. It is hoped that the outcome from this study will promote better understanding, ensure consistency of implementation, and to aid investigators in explaining and justifying their actions during search and seizure in court.
Art is an artistic method of using digital technologies as a part of the generative or creative process. With the advent of digital currency and NFTs (Non-Fungible Token), the demand for digital art is growing aggressively. In this manuscript, we advocate the concept of using deep generative networks with adversarial training for a stable and variant art generation. The work mainly focuses on using the Deep Convolutional Generative Adversarial Network (DC-GAN) and explores the techniques to address the common pitfalls in GAN training. We compare various architectures and designs of DC-GANs to arrive at a recommendable design choice for a stable and realistic generation. The main focus of the work is to generate realistic images that do not exist in reality but are synthesised from random noise by the proposed model. We provide visual results of generated animal face images (some pieces of evidence showing a blend of species) along with recommendations for training, architecture and design choices. We also show how training image preprocessing plays a massive role in GAN training.
Open access
2 source records
Generative Adversarial Networks and Image Synthesis
The last decades have seen video production and consumption rise significantly: TV/cinematography, social networking, digital marketing, and video surveillance incrementally and cumulatively turned video content into the predilection type of data to be exchanged, stored, and processed. Belonging to video processing realm, video fingerprinting (also referred to as content-based copy detection or near duplicate detection ) regroups research efforts devoted to identifying duplicated and/or replicated versions of a given video sequence (query) in a reference video dataset. The present paper reports on a state-of-the-art study on the past and present of video fingerprinting, while attempting to identify trends for its development. First, the conceptual basis and evaluation frameworks are set. This way, the methodological approaches (situated at the cross-roads of image processing, machine learning, and neural networks) can be structured and discussed. Finally, fingerprinting is confronted to the challenges raised by the emerging video applications ( e.g. , unmanned vehicles or fake news) and to the constraints they set in terms of content traceability and computational complexity. The relationship with other technologies for content tracking ( e.g., DLT - Distributed Ledger Technologies) are also presented and discussed.
Open access
Advanced Steganography and Watermarking Techniques
Abstract With the development of 5G, the wireless Internet of Things (IoT) has become possible; how to provide privacy protections for the communication of IoT devices in a more vulnerable wireless transmission environment is a huge challenge. Thus, steganography is introduced as a safe and effective technology. Blockchain systems have been widely used in the area of steganography. Several works attempted to embed covert data into transactions in public blockchain systems such as Bitcoin, Ethereum and Monero. However, most of them merely focus on putting covert data into certain fields in transactions based on cryptographic algorithms. In this paper, a Covert Transaction Recognition (CTR) model is proposed by the Text Convolutional Neural Networks and Back Propagation Neural Networks. When utilizing the covert data-embedded field for recognizing, our CTR model can attain 0.79 precision and 0.83 recall on average for seven covert transaction construction schemes. The precision and recall can increase by at most 43 and 47%, respectively, if other unembedded fields were additionally exploited for recognition. We further propose a Practical Covert Transaction Construction (PCTC) model. This model fixes the contents in the embedded fields of the constructed transactions, and generates the contents in other fields using Generative Adversarial Networks. Experimental results demonstrated that the precision and recall are greatly decreased when identifying the covert transactions generated by our PCTC model. The data underlying this article are available in ‘covert-transaction-model’, at https://github.com/1997mint/covert-transaction-model.
Advanced Steganography and Watermarking Techniques