Aug 2026· Journal of King Saud University: Computer and Information Sciences· Vol 38· 0 citations· 23 references
TL;DR
A comprehensive trading framework that incorporates state-of-the-art methodologies and algorithms to simulate the entire AI image trading process and supports multiple trading mechanisms, including Blind English Sealed-Bid Auctions (BESEA), fixed-price auctions with a first-come, first-served (FCFS) model, Dutch auctions with royalty redistribution, and fractionalized auction trading.
Abstract
In the era of artificial intelligence, the AI-generated image (AIGI) market is an emerging sector that faces significant challenges related to ownership, privacy, and security. These issues, especially prevalent in NFT markets, can be effectively addressed by the integration of advanced technologies such as blockchain, the InterPlanetary File System (IPFS), and Quantum Key Distribution (QKD). This study proposes a comprehensive trading framework that incorporates state-of-the-art methodologies and algorithms to simulate the entire AI image trading process. For image generation, the framework utilises diffusion models (LCM-LoRA + SDXL) and Generative Adversarial Networks (GANs), employing LCM-LoRA and LCMScheduler from Stable Diffusion XL Base 1.0 to accelerate image generation and reduce inference steps. Implementation is carried out using PyTorch and the Diffusers library, running on a CUDA-enabled GPU. The generated images are securely stored in the distributed IPFS storage system, while decentralised trading is facilitated through integration with the Hyperledger MiniFab tool. The framework supports multiple trading mechanisms, including Blind English Sealed-Bid Auctions (BESEA), fixed-price auctions with a first-come, first-served (FCFS) model, Dutch auctions with royalty redistribution, and fractionalized auction trading. To ensure secure communication between buyers and sellers, the BB84 QKD protocol is employed to generate a shared secret key with information-theoretic security. The generated key is processed through key sifting to derive a symmetric key, which is zero-padded to the 256-bit length required by AES-256-CBC. It is then directly used as the encryption key to encrypt AI-generated images and their associated metadata before storage on IPFS. Experimental evaluation across four auction mechanisms and up to 250 NFTs shows the Dutch auction achieving the highest sales volume (up to 211 NFTs sold) and the Fractionalized auction the highest revenue ( 98,270). The IPFS storage maintains sub-0.75-second upload latency with 100% file verification success. Blockchain-layer benchmarking across 100–500 participants records mean chaincode latency ranging from approximately 22 to 53 seconds and throughput of 0.018–0.045 TPS.
The inherent challenge of balancing scalability, security, and decentralization – commonly termed the blockchain trilemma – continues to hinder the adoption of distributed systems. This paper presents InternxtChain, a decentralized storage framework designed to address this trilemma through a novel integration of erasure-coded sharding, zero-knowledge succinct non-interactive arguments of knowledge (zk-SNARKs), and a sharded Proof-of-Storage consensus mechanism. By leveraging aggregated BLS-381 signatures and distributed redundancy protocols, the framework achieves a throughput of 2,800 transactions per second with a latency of 420 milliseconds across 1,024 nodes, surpassing Filecoin by a factor of 3.5 and Ethereum’s capacity by 165 times. The system maintains 99.9% data integrity even under adversarial conditions involving 30% Byzantine nodes. Additionally, InternxtChain reduces storage costs to $0.002 per gigabyte, representing an 85% reduction compared to centralized alternatives like AWS S3. Empirical evaluations demonstrate linear scalability to 4,200 transactions per second with 2,048 nodes, alongside hardware affordability at $180 per node. These advancements not only outperform decentralized platforms in throughput by 2.8 times but also ensure GDPR-compliant data sovereignty, positioning InternxtChain as a pioneering solution for Web3 ecosystems seeking to harmonize enterprise-grade performance with decentralized trustlessness.
Saha Reno· South African Computer Journ...· 1 citation
This work develops a Blockchain-Enabled Federated Learning (BCFL) framework to address some of the major concerns in federated learning: the use of a central server, the lack of transparency/traceability during the training process and the risk of a malicious participant leaking private information. By utilizing the blockchain as an intermediary to aggregate all the local models trained at each participants location, the BCFL framework ensures the integrity of the aggregated model, provides a transparent record of all transactions and prevents tampering. In addition, this framework utilizes the Interplanetary File System (IPFS) to allow nodes to store their own model parameters locally and provides a decentralized method of managing those parameters. The system uses a lightweight hash-based verification mechanism that allows model updates to be verified using their Content Identifiers (CIDs) on the blockchain, without sending the raw parameters to a central authority. Tests using the MNIST, Fashion-MNIST, and CIFAR-10 datasets show that the BCFL framework improves the accuracy of the Global model in the presence of a 20% label-flipping data poisoning attack by 31.65% to 42.40% compared to standard FL baselines without outlier defense. The integration of blockchain consensus and IPFS storage causes a predictable computational training latency overhead of around 7.5%-8.2%. Yet, the framework achieves baseline predictive accuracy (on average 88.49% on CIFAR-10), which indicates a practical and quantifiable trade-off between computing and decentralized security.
J. Rauthan, Rohan Verma, Surabhi Lingwal et al.· Journal of Intelligent &...· 0 citations
Fast developments in the field of artificial intelligence have made possible the emergence of hyper-realistic
synthesized media dubbed deepfakes that constitute a significant challenge for digital trust, public communications, and
forensics. Current solutions for detecting media deepfakes employ deep learning models that look for visual and temporal
inconsistencies in altered images and videos. But these methods are reactive and cannot keep up with the development of
the adversarial models meant to circumvent the detection algorithms. In order to overcome this problem, this paper offers
a proactive solution that utilizes Public Key Infrastructure (PKI) and blockchain technology for establishing authenticity
of the media at its moment of capturing. In particular, the solution hashes the original media with a SHA-256 hash
function and saves it on a blockchain compatible with the Ethereum Virtual Machine (EVM) using smart contracts.
Verification of the media involves re-computing its hash and comparing it to the record in the blockchain. Any
modifications to the media will be revealed during the process. A proof-of-concept implementation is used to assess the
framework in terms of transaction time, gas consumed, and robustness to post-production modifications. Experiments
show that the proposed approach allows achieving zero-trust, low-complexity and secure verification of the content
integrity and strengthening digital journalism.
H. V, D. C. S., V. G et al.· International Journal of Inn...· 0 citations
The rapid advancement of generative artificial intelligence (GAI) has led to the widespread adoption of AI-generated content (AIGC), which generally leverages generative diffusion models (GDMs) to create high-quality multimodal content. By integrating mobile edge computing (MEC) and model compression techniques, edge AIGC can provide low-latency services for mobile users (MUs) at the network edge, thereby unlocking greater potential. However, such a paradigm is vulnerable to critical security risks, such as tampering and plagiarism attacks on AIGC products. To protect the copyright of AIGC products, blockchain technology has been introduced as a promising solution. Nevertheless, most existing studies on the integrated blockchain-edge AIGC framework focus primarily on management mechanisms, while neglecting the inherent resource allocation problem for the tightly coupled AIGC inference and blockchain consensus processes, which severely limits the overall system efficiency. In this work, we propose a blockchain-enhanced edge AIGC service framework over MEC networks, where multiple edge servers (ESs) act as both model hosts generating contents for MUs and miners participating in blockchain consensus. In such a framework, we study the joint optimization of AIGC inference and blockchain consensus, including MU association, inference steps, as well as communication and computation resource allocation, aiming to maximize the total system utility. To tackle the challenges posed by mixed discrete and continuous optimization variables, we decompose the orginal problem into four sequential subproblems and propose a Joint MU association, Inference step allocation, Bandwidth allocation, Power allocation, and Streaming multiprocessor allocation (JMIBPS) algorithm based on Markov approximation, interior point method, and successive convex approximation. Simulation results validate the effectiveness of the proposed algorithm, which improves the total system utility by at least 10.21% compared with representative benchmark schemes.
Licheng Ye, Zehui Xiong, Yuan Luo et al.· IEEE Transactions on Network...· 0 citations
Abstract This paper presents a secure blockchain-enabled Automatic Number Plate Recognition (ANPR) framework for Intelligent Transportation Systems (ITS), combining lightweight YOLO-based license plate detection, OCR-based character recognition, and Ethereum smart contracts for tamper-resistant vehicle data management. The study investigates the inference performance of recent object detection architectures, namely YOLOv11, YOLOv12, and YOLO26, on Raspberry Pi 5 and NVIDIA Jetson Nano edge devices. Furthermore, optimizations for ONNX and TensorRT are explored to enhance inference efficiency on embedded hardware. Experimental results demonstrate complementary strengths among the evaluated models. YOLOv11n achieved the best overall detection performance, obtaining the highest recall (0.945), F1-score (0.9645), and mAP@0.5:0.95 (0.692), while YOLOv11n and YOLOv12n achieved identical precision (0.985) and mAP@0.5 (0.963). YOLO26 demonstrates the best deployment efficiency, reducing inference latency to 33.4 ms on Raspberry Pi (ONNX) and 38.9 ms on Jetson Nano, making it suitable for edge applications. Model optimization significantly accelerates inference, reducing YOLOv11 latency on Raspberry Pi from 98.2 ms to 38.3 ms after ONNX conversion. The results demonstrate that the proposed framework effectively balances detection accuracy, computational efficiency, and data security, making it a promising solution for smart parking and next-generation ITS applications.
Nesrine Affes, Jalel Ktari, H. Hamam· Journal of Information Assur...· 0 citations
The rapid development of AIGC poses unprecedented challenges to digital copyright management, including training data disputes, originality determination, and derivative tracing. This paper proposes a novel copyright governance framework integrating perceptual hashing and blockchain for AIGC content. A fine-tuned CNN generates robust perceptual hashes that capture AIGC characteristics while maintaining consistency across variations. The framework uses contrastive and adversarial training. Hashes are registered on a blockchain with smart contracts for automated management. A hierarchical tracing mechanism links generated content to training data sources via multi-level similarity analysis. Experiments on a comprehensive AIGC dataset show 98.7% identification accuracy, 97.8% average hash consistency, and 94.5% tracing accuracy for derivative works, addressing critical gaps in digital rights management.
Zhaoxiong Meng, Rukui Zhang, Bin Cao et al.· Annual International Compute...· 0 citations
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.