Atsuki Koyama, Kentaroh Toyoda, Manato Fujimoto, Thi Hong Tran
The rapid advancement of deepfake technology poses serious risks, including financial fraud and political misinformation, demanding robust methods for verifying image content authenticity. While the C2PA standard and zero-knowledgeproof-based methods provide an image content authenticity proving mechanism, the existing solutions struggle to efficiently support privacy-preserving edits and iterative modifications. To address these challenges, we propose zk-REAL (Zero-Knowledge-Based Protocol for Repeated Image Edit Authenticity Proof with Lattice Hashing), a framework that leverages a lightweight lattice-based hashing scheme within a zero-knowledge proof system. Our approach significantly reduces computational overhead, enabling faster proof generation and smaller proof size even for high-resolution images. Additionally, the updatability of our hashing method supports iterative edits, such as mosaicking or partial modifications, by minimizing redundant computations. Finally, to ensure compatibility with the C2PA ecosystem and conventional signature verifications, we integrate SHA-256 outside of the zero-knowledge circuit. Our evaluation shows up to a 29% reduction in computational costs for proof generation, showcasing the potential of zk-REAL in practical content authenticity verification scenarios.
Open access
2 source records
Advanced Steganography and Watermarking Techniques
Abstract This paper presents a novel method for decentralized storage in deep-learning-based face recognition systems using the Hierarchical Navigable Small World (HNSW) algorithm. The proposed solution utilizes Ethereum smart contracts, which acts as highly available data storage systems for storing identifiable data for authorized personnel. In addition, the solution is integrated with a centralized vector database that is in charge of vector indexing, searching and associating face embeddings to an identity on the Ethereum blockchain with anonymous hashes. Vector indexing and search processes involve different machine learning algorithms that enable computations to be carried out in a reasonable time with good matching accuracy. Specifically, we compared different approaches and selected the HNSW algorithm. Accordingly, we successfully implemented a prototype of a reliable and privacy-focused decentralized face identification system for areas under government surveillance, such as customs inspection sites. In our measurements, the system could handle 20,000 face vectors easily with high matching accuracy, and the performance could be further improved using more powerful hardware. Finally, we also propose additional methods to further scale up the system to handle millions of face vectors.
Yilin Ye, Qian Zhu, Shishi Xiao, Kang Zhang ยท 5 authors
Image search is an essential and user-friendly method to explore vast galleries of digital images. However, existing image search methods heavily rely on proximity measurements like tag matching or image similarity, requiring precise user inputs for satisfactory results. To meet the growing demand for a contemporary image search engine that enables accurate comprehension of users' search intentions, we introduce an innovative user intent expansion framework. Our framework leverages visual-language models to parse and compose multi-modal user inputs to provide more accurate and satisfying results. It comprises two-stage processes: 1) a parsing stage that incorporates a language parsing module with large language models to enhance the comprehension of textual inputs, along with a visual parsing module that integrates an interactive segmentation module to swiftly identify detailed visual elements within images; and 2) a logic composition stage that combines multiple user search intents into a unified logic expression for more sophisticated operations in complex searching scenarios. Moreover, the intent expansion framework enables users to perform flexible contextualized interactions with the search results to further specify or adjust their detailed search intents iteratively. We implemented the framework into an image search system for NFT (non-fungible token) search and conducted a user study to evaluate its usability and novel properties. The results indicate that the proposed framework significantly improves users' image search experience. Particularly the parsing and contextualized interactions prove useful in allowing users to express their search intents more accurately and engage in a more enjoyable iterative search experience.
We study the task of generating profitable Non-Fungible Token (NFT) images from user-input texts. Recent advances in diffusion models have shown great potential for image generation. However, existing works can fall short in generating visually-pleasing and highly-profitable NFT images, mainly due to the lack of 1) plentiful and fine-grained visual attribute prompts for an NFT image, and 2) effective optimization metrics for generating high-quality NFT images. To solve these challenges, we propose a Diffusion based generation framework with Multiple Visual-Policies as rewards (i.e., Diffusion-MVP) for NFT images. The proposed framework consists of a large language model (LLM), a diffusion-based image generator, and a series of visual rewards by design. First, the LLM enhances a basic human input (such as "panda") by generating more comprehensive NFT-style prompts that include specific visual attributes, such as "panda with Ninja style and green background." Second, the diffusion-based image generator is fine-tuned using a large-scale NFT dataset to capture fine-grained image styles and accessory compositions of popular NFT elements. Third, we further propose to utilize multiple visual-policies as optimization goals, including visual rarity levels, visual aesthetic scores, and CLIP-based text-image relevances. This design ensures that our proposed Diffusion-MVP is capable of minting NFT images with high visual quality and market value. To facilitate this research, we have collected the largest publicly available NFT image dataset to date, consisting of 1.5 million high-quality images with corresponding texts and market values. Extensive experiments including objective evaluations and user studies demonstrate that our framework can generate NFT images showing more visually engaging elements and higher market value, compared with state-of-the-art approaches.
Open access
3 source records
Generative Adversarial Networks and Image Synthesis
Travis C. Cuvelier, Takashi Tanaka, Robert W. Heath
We propose an adaptive coding approach to achieve linear-quadratic-Gaussian (LQG) control with near-minimum bitrate prefix-free feedback. Our approach combines a recent analysis of a quantizer design for minimum rate LQG control with work on universal lossless source coding for sources on countable alphabets. In the aforementioned quantizer design, it was established that the quantizer outputs are an asymptotically stationary, ergodic process. To enable LQG control with provably near-minimum bitrate, the quantizer outputs must be encoded into binary codewords efficiently. This is possible given knowledge of the probability distributions of the quantizer outputs, or of their limiting distribution. Obtaining such knowledge is challenging; the distributions do not readily admit closed form descriptions. This motivates the application of universal source coding. Our main theoretical contribution in this work is a proof that (after an invertible transformation), the quantizer outputs are random variables that fall within an exponential or power-law envelope class (depending on the plant dimension). Using ideas from universal coding on envelope classes, we develop a practical, zero-delay version of these algorithms that operates with fixed precision arithmetic. We evaluate the performance of this algorithm numerically, and demonstrate competitive results with respect to fundamental tradeoffs between bitrate and LQG control performance.
Secure retrieval of remote sensing images in an outsourced cloud environment garners considerable attention. Since the cloud service provider (CSP) is considered as a semitrusted third party that may return incorrect retrieval results to save computational resources or defraud retrieval fees for profit, it becomes a critical challenge to achieve secure and verifiable remote sensing image retrieval. This article presents a secure retrieval and blockchain-assisted verifiable scheme for encrypted remote sensing images in the cloud environment. In response to the characteristic that geographical objects in remote sensing images with clear category attributes, we design a remote sensing image retrieval method to facilitate secure and efficient retrieval. In addition, we propose a verifiable method combined with blockchain and Merkle trees for checking the integrity and correctness of the storage and retrieval services provided by CSP, which can replace the traditional third-party auditor. The security analysis and experimental evaluation demonstrate the security, verifiability, and feasibility of the proposed scheme, achieving secure remote sensing image retrieval while preventing malicious behavior of CSP.
Tu Bui, Daniel Cooper, John Collomosse, Mark Bell ยท 11 authors
We present ARCHANGEL; a novel distributed ledger based system for assuring the long-term integrity of digital video archives. First, we describe a novel deep network architecture for computing compact temporal content hashes (TCHs) from audio-visual streams with durations of minutes or hours. Our TCHs are sensitive to accidental or malicious content modification (tampering) but invariant to the codec used to encode the video. This is necessary due to the curatorial requirement for archives to format shift video over time to ensure future accessibility. Second, we describe how the TCHs (and the models used to derive them) are secured via a proof-of-authority blockchain distributed across multiple independent archives. We report on the efficacy of ARCHANGEL within the context of a trial deployment in which the national government archives of the United Kingdom, Estonia and Norway participated.
In order to prevent sensitive data tampering in the application of security monitoring, intelligent traffic, and other sensitive Internet of Things, the research on WMSN (wireless multimedia sensor networks) application system based on blockchain and IPFS (InterPlanetary File System) is of great significance. However, WMSN data are characterized by high dimensionality, large scale, and multiple types, so it is challenging to search WMSN data efficiently over blockchain system. This paper proposed a novel One Permutation with Rotation and cross-polytope locality-sensitive hashing (OPRCP) method of approximate nearest neighbor binary query for querying binary hybrid data in the form of WMSN multimedia data (containing two hybrid types of data, such as image-text and image-audio). Firstly, a binary hybrid data index was built with the method of locality-sensitive hashing (LSH) to retain content similarity among original data objects for performing accurate queries. Secondly, the approximate nearest neighbor search strategy was used in place of the nearest neighbor strategy, to reduce querying time. Finally, a binary hybrid data model was employed to cope with multiple types of data in WMSN and carry out collaborative search of binary hybrid data. The experimental results show that compared with other mainstream methods, the proposed OPRCP method is widely adaptive to massive high-dimensional data in multiple types and can improve the accuracy of query results. The OPRCP method exhibits good performance, effectively saves resources, and reduces query time for a variety of datasets. It is an effective solution to the binary hybrid search of approximate neighbors, and it is applicable to the WMSN data search based on smart contracts in WMSN blockchain systems.
In this article, we introduce a prototype of an innovative technology for proving the origins of captured digital media. In an era of fake news, when someone shows us a video or picture of some event, how can we trust its authenticity? It seems that the public no longer believe that traditional media is a reliable reference of fact, perhaps due, in part, to the onset of many diverse sources of conflicting information, via social media. Indeed, the issue of "fake" reached a crescendo during the 2016 U.S. Presidential Election, when the winner, Donald Trump, claimed that The New York Times was trying to discredit him by pushing disinformation. Current research into overcoming the problem of fake news does not focus on establishing the ownership of media resources used in such stories-the blockchain-based application introduced in this article is technology that is capable of indicating the authenticity of digital media. Put simply, using the trust mechanisms of blockchain technology, the tool can show, beyond doubt, the provenance of any source of digital media, including images used out of context in attempts to mislead. Although the application is an early prototype and its capability to find fake resources is somewhat limited, we outline future improvements that would overcome such limitations. Furthermore, we believe that our application (and its use of blockchain technology and standardized metadata) introduces a novel approach to overcoming falsities in news reporting and the provenance of media resources used therein. However, while our application has the potential to be able to verify the originality of media resources, we believe that technology is only capable of providing a partial solution to fake news. That is because it is incapable of proving the authenticity of a news story as a whole. We believe that takes human skills.