In client-server applications such as copyright protection and content moderation, learning-based perceptual hashing compresses images into compact binary codes whose Hamming distances approximate perceptual similarity. Clients then transmit these codes to servers for comparison. However, this approach faces dual challenges: algorithmically, how to effectively balance robustness and discriminability while mitigating bit imbalance issues; protocol-wise, transmitting these hashes compromises client privacy through content inference and cross-platform user tracking. To address these challenges, we propose a trustworthy privacy-preserving framework that integrates deep hashing with zero-knowledge proofs. The framework comprises: (1) A robust deep hashing module that generates discriminative binary codes by optimizing a composite objective function composed of the Angular Triplet and quantization losses, while using a multi-scale strategy to correct bit imbalance. (2) A privacy-preserving similarity comparison protocol based on Sumcheck and Logarithmic Lookup, which enables clients to locally prove batch Hamming distance relationships against public dataset entries without disclosing their hash values. We conducted comprehensive evaluations to demonstrate the practicality and efficiency of our design compared to existing schemes. Source code is available at https://github.com/mengdehong/zkph.
Advanced Steganography and Watermarking Techniques
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
With the rapid growth of blockchain-based Non-Fungible Tokens (NFTs), data trading has evolved to incorporate NFTs for ownership verification. However, the NFT ecosystem faces significant challenges in copyright protection, particularly when malicious buyers slightly modify the purchased data and remint it as a new NFT, infringing upon the original ownerโs rights. In this paper, we propose a copyright-preserving data trading protocol to address this challenge. First, we introduce the Merkle Feature Tree (MFT), an enhanced version of the traditional Merkle Tree that incorporates an AI-powered feature layer above the data layer. Second, we design a copyright challenge phase during the trading process, which recognizes the data owner with highly similar feature vectors and earlier on-chain timestamp as the legitimate owner. Furthermore, to achieve efficient and low-gas feature vector similarity computation on blockchain, we employ Locality-Sensitive Hashing (LSH) to compress high-dimensional floating-point feature vectors into single uint256 integers. Experiments across multiple image feature extraction models show that LSH maintains a high F1 score after compression, effectively supporting similarity-based copyright challenges. Experimental results on the Ethereum Sepolia testnet demonstrate NMFTโs scalability with sublinear growth in gas consumption while maintaining stable latency.
With the growing popularity of cloud services, companies and individuals outsource images to cloud servers to reduce storage and computing burdens. The images are encrypted before outsourcing for privacy protection. It has become urgent to solve the privacy-preserving image retrieval problem on the cloud. There are three main challenges in this area. First, how can we achieve high retrieval accuracy on the encryption domain? Second, how can we improve efficiency in large-scale encrypted image retrieval? Third, how can we ensure the reliability of the retrieval results? The existing schemes only consider some of these characteristics and the retrieval accuracy is insufficient. In this paper, we propose a privacy-preserving large-scale image retrieval framework with vision graph convolutional neural network hashing (ViGH). To the best of our knowledge, this is the first framework that is able to address all the above challenges with more advanced accuracy performance. To be specific, cycle-consistent adversarial networks and vision graph convolutional networks (ViG) are utilized to increase retrieval accuracy. By embedding encrypted images into hash codes, we can obtain high retrieval efficiency by Hamming distances. Cloud servers store the hash codes on the blockchain (Ethereum). The retrieval algorithm on the smart contracts and the consensus mechanism of blockchain ensure reliability of the retrieval results. The experimental results on three common datasets verify the effectiveness and efficiency of the proposed privacy-preserving image retrieval framework. The reliability of the retrieval results is ensured by the consensus mechanism of blockchain with no need for verification.
Elena Andreeva, Rishiraj Bhattacharyya, Arnab Roy, Stefano Trevisani
ZK-SNARKs, a fundamental component of privacyoriented payment systems, identity protocols, or anonymous voting systems, are advanced cryptographic protocols for verifiable computation: modern SNARKs allow to encode the invariants of a program, expressed as an arithmetic circuit, in an appropriate constraint language from which short, zero-knowledge proofs for correct computations can be constructed. One of the most important computations that is run through SNARK systems is the verification of Merkle tree (MT) opening proofs, which relies on the evaluation of a fixed-input-length (FIL) cryptographic compression function over binary MTs. As classical, bit-oriented hash functions like SHA-2 are not compactly representable in SNARK frameworks, Arithmetization-Oriented (AO) cryptographic designs have emerged as an alternative, efficient solution. Today, the majority of AO compression functions are built from permutation-based hashing modes, such as Sponge. While this approach allows cost savings, compared to blockcipher-based modes, as it does not require key-scheduling, AO blockcipher schedulers are often cheap to compute. Furthermore, classical bitoriented cryptography has long studied how to construct provably secure compression functions from blockciphers, following the Preneel-Govaerts-Vandewalle (PGV) framework. The potential efficiency gains together with the strong provable security foundations in the classic setting, motivate the study of AO blockcipher-based compression functions. In this work, we propose AO PGV-LC and PGV-ELC, two AO blockcipher-based FIL compression modes inspired by and extending the classical PGV approach, offering flexible input and output sizes and coming with provable security guarantees in the AO setting. We prove the collision and preimage resistance in the ideal cipher model, and give bounds for collision and opening resistance over MTs of arbitrary arity. We compare experimentally the AO PGV-ELC mode over the HADES blockcipher with its popular and widely adopted Sponge instantiation, POSEIDON, and its improved variant POSEIDON2. Our resulting constructions are up to 3ร faster than POSEIDONAND 2ร faster than POSEIDON2 in native x86 execution, and up to 50% faster in the Groth16 SNARK framework. Finally, we study the benefits of using MTs of arity wider than two, proposing a new strategy to obtain a compact R1CS constraint system in such case. In fact, by combining an efficient parametrization of the HADES blockcipher over the PGV-ELC mode, together with an optimal choice of the MT arity, we measured an improvement of up to 9ร in native MT construction time, and up to 2.5ร in proof generation time, compared to POSEIDON over binary MTs.
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.
Zero-knowledge proof (ZKP) is a popular cryptographic strategy for building a trusted environment, which can be applied to blockchain, electronic voting, and other scenarios. However, ZKP involves a number of computationally intensive operations that limit its widespread adoption in time-sensitive practical applications. The multi-scalar multiplication (MSM) dominates the computations and takes over 70% of the total computation time. This paper proposes a GPU-based acceleration method for ZKP by designing several optimization techniques for MSM. First, this paper constructs a formal mathematical formula of the Pippenger algorithm, which provides a theoretical optimization framework for MSM. Second, by parallelizing the prefix sum, the time complexity of the bucket reduction part of MSM is reduced from $\mathcal{O}\left( {3 \times {2^C}} \right)$ to $\mathcal{O}\left( {2 \times {2^C}} \right)$. Finally, this paper also analyzes the influence of group size on the final calculation time under different data scales and gives a suitable range of group sizes. Compared to the state-of-the-art method, our method can achieve 1.01ร to 1.12ร for throughput.
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.
In this work, we present SONAR, a web-based tool for multimodal exploration of Non-Fungible Token (NFT) inspiration networks. SONAR is conceived to support both creators and traders in the emerging Web3 by providing an interactive visualization of the inspiration-driven connections between NFTs, at both individual level and collection level. SONAR can hence be useful to identify new investment opportunities as well as anomalous inspirations. To demonstrate SONAR's capabilities, we present an application to the largest and most representative dataset concerning the NFT landscape to date, showing how our proposed tool can scale and ensure high-level user experience up to millions of edges.
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.
With the proliferation of cloud services, the work of large-scale image retrieval is carried out on remote cloud become a trend in order to get rid of the storage burden and computation. However, traditional retrieval work based on centralized cloud services is considered to take risk in giving away users' privacy in many researches. We need a secure way for retrieving and storing images by decentralized approach. In this paper, we propose a decentralized scheme named PPIRB(An Privacy-Preserving Image Retrieval Scheme Base on Blockchain) for retrieving images based on blockchain. We used the data structure called amplifying locality sensitive hashing (ALSH) to improve search accuracy. Searchable symmetric en-cryption(SSE) and ALSH used to realize the encryption retrieval of image index on the blockchain. Our scheme also uses IPFS to replace the cloud server to realize distributed storage, and uses secret sharing scheme to realize the access control. We implemented and evaluated the scheme in Ethereum, and the results show that our scheme is efficient and accurate in finding similar images while preserving privacy. The overall overhead is reasonable.
This paper proposes a blockchain-based traceability system of photos. Thanks to a novel scheme that securely chains certificates of image data originating from a trusted origin certificate, the system authenticates the provenance of original and converted images, e.g., which digital camera created it. The system requires a Public Key Infrastructure (PKI) of digital cameras to authenticate the trusted origin certificate signed by the certified digital camera. It does not require a PKI of image conversion software. The proposed solution is suitable for the traceability system of photos on the Internet as the scheme of chaining certificates applies to any image conversion software, including open source-based photo editing applications and cloud server software that converts image data of photos. We have implemented a prototype of the traceability system using Ethereum as a permissioned blockchain and evaluated the system's feasibility.
Advanced Steganography and Watermarking Techniques
Xianxian Li, Jie Li, Feng Yu, Xuemei Fu ยท 6 authors
Encrypted image retrieval may return incorrect or incomplete results due to threats from malicious cloud servers. Most of the existing solutions focus on the efficiency and accuracy of retrieval, lack of verification of the completeness of search results, to achieve the reliability of search results and the transparency of the search process, we explore characteristic such as the decentralization and tamper-proof of blockchain, proposed a blockchain-based encrypted image retrieval scheme. This scheme stores the encrypted index on the blockchain (Ethereum), through the blockchain consensus mechanism and the function of searching on the smart contract, ensures the integrity and correctness of search results, then outsources the corresponding encrypted images to the cloud server to reduce storage cost, and designs a double-layer index structure using the bag of visual word model and simhash in the process of image similarity index. Experiments show that the reliability, high retrieval efficiency, and precision of the scheme also have a good privacy protection effect.
Advanced Steganography and Watermarking Techniques
Multimedia data, especially images are increasing dramatically. Images published on the Web are more often facing the risk of being tampered or manipulated since their content is easily mutable. Using blockchain technology provides advantages and, at the same time, challenges when dealing with this issue due to the following reasons: (a) data in a blockchain are well saved and immutable and (b) adding the data directly to a blockchain may consume much time which makes it computationally and economically expensive. Thus, we propose a blockchain-based solution which considers two key aspects: First, using a blockchain to register information about ownership and copyrights for authors, as well as descriptive information of an image, used to detect copyright violations. Second, avoiding insertion of raw image data into the blockchain, but storing only unique descriptive metadata about the images, allowing for a more efficient implementation of the system. This work considers different well-known image matching approaches to validate the power of the proposed approach, which allows for an efficient checking of violations of copyrights for a given image.
Advanced Image and Video Retrieval Techniques
Advanced Steganography and Watermarking Techniques
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.
S. Armeni, D. Christodulakis, Ioannis Kostopoulos, Yannis C. Stamatiou ยท 5 authors
In this work, a method for proving copyright ownership is presented that is based on Zero Knowledge Interactive Proof (ZKIP) protocols for computationally intractable problems. The utilized problem is the 3-coloring problem, which consists in assigning one of three available colors to the vertices of a graph so that no two adjacent vertices have the same color. Using the presumed computational intractability of this problem, the construction of large signatures is proposed so that they represent adjacency matrices of random, 3-colorable graphs. Since it is easy to construct large graphs with a prescribed 3-coloring of their vertices whereas it is difficult to discover such a 3-coloring, the owner of a copyrighted digital piece of work (e.g. image, audio, video) may easily generate a random 3-colorable graph, embed it in the digital object and then use the knowledge of the 3-coloring in debates over the objectโs ownership. Due to the intractability of the 3-coloring problem, only the owner is able to produce it sufficiently fast in an ownership challenge so as to convince a third party that the graph was indeed embedded in the object by herself/himself. Since graphs with maximum possible resistance to well-known coloring algorithms is required, we exploit some relatively recent experimental and theoretical findings suggesting that hard 3-coloring instances are found among graphs having a vertices to edges ratio around a specific threshold value. The proposed scheme has the additional advantage that disclosing the signature is of no consequences since it is essentially the knowledge of a characteristic of the signature, i.e. the 3-coloring of the graph it represents, that enables one to use it as proof of ownership of some digital object that contains it. Even if someone managed to locate and extract the signature, to use it would require a fast solution to a computationally intractable problem on some hard instance. Our proposal represents a shift from signatures that are simply viewed as bit sequences to signatures with properties that stem from their interpretation as instances of computationally intractable problems.
Advanced Steganography and Watermarking Techniques