Blockchain technology has recently been the subject of investigation as a potential solution to security issues plaguing IoT networks. However, when dealing with a large number of IoT gadgets and the massive amounts of data produced by these networks, the inherent scalability difficulties of blockchain-based systems become obvious. Nevertheless, there are areas where the permissioned Blockchain falls short, and these include throughput and scalability. Incorporating data science methodologies, this study proposes a way to address permissioned Blockchain's scalability problem. With a variable number of transactions, the scalability study of the suggested solution is done in the hyperledger fabric architecture, which improves scalability. Because of this, we address these issues in this research by using a lightweight consensus approach. We provide a system for handling IoT data that is scalable and built on blockchain technology. It can handle data from a large number of gadgets. To guarantee improved efficiency and effectiveness in resource-constrained IoT networks, this system employs the Delegated Proof of Stake (DPoS) consensus process. DPoS mitigates the performance and effectiveness deterioration in blockchain-based IoT networks by using a certain amount of elected delegates to verify and approve transactions. It is a lightweight consensus mechanism. In this article, we used Docker, the XGBoost mapping model, and the Interplanetary File System (IPFS) to assess the network's performance in relation to latency, resource consumption, and throughput. The four components of our distributed storage study were latency, throughput, resource consumption, and the duration and speed of file uploads. We found that our framework has a low latency of less than 0.976 ms in our empirical results. One state-of-the-art consensus method, Proof of Stake (PoS), is outperformed by the suggested method. We also show that the suggested method works well for Internet of Things (IoT) uses that call for minimal latency or efficient use of resources.
In the rapidly evolving landscape of distributed computing, the integration of fog computing, cloud paradigms, and blockchain technology has emerged as an innovative approach to enhance the efficiency and security of task scheduling. This article introduces a novel method using the Sparrow Search Algorithm (SSA), along with its decomposition variant SSA/D, to optimize task scheduling within this integrated system. This paper presents a comprehensive framework that outlines the unique characteristics of fog, cloud, and blockchain environments, addressing their individual constraints while leveraging their combined strengths. The adaptability and robustness of SSA/D are employed to address the multi-objective nature of the scheduling problem, focusing on minimizing latency, energy consumption, and financial cost while ensuring data integrity through the blockchain's immutable ledger. We have employed the Sparrow Search Algorithm (SSA), a recent optimization method proven effective in other applications. Our main contribution is the integration of a decomposition strategy to enhance the exploration of the search space and enable parallel execution of the SSA process. Experimental results show that the proposed approach outperforms existing algorithms in terms of both efficiency and effectiveness, providing significant improvements over popular task scheduling metaheuristics. This paper not only offers a new algorithmic solution but also sets a precedent for future research in integrated fog-cloud-blockchain systems, with a view towards integrating machine learning techniques to further optimize these problems.
Blockchain enhances the security and interoperability of Internet of Vehicles (IoV) systems by serving as a secure and decentralized platform for data sharing. The rapid growth of IoV data makes it challenging to store the entire blockchain on edge nodes with limited storage resources due to the blockchain’s immutability. Redactable blockchain represents a potential solution for enabling the controlled modification of data on blocks. However, current redactable blockchain schemes suffer from high-computational overhead and lack support for stateful redaction and consistency checking. In this article, we propose a secure and efficient decentralized chameleon hash scheme (CHSTS) based on Schnorr threshold signatures. CHSTS allows${t}$-out-of-${n}$edge nodes to collaborate with the transaction proposer to compute chameleon hash collisions, enabling modification and deletion of block data without breaking the hash links between the blocks. We then construct a redactable blockchain utilizing CHSTS to alleviate the storage limitations of edge nodes. To ensure consistency checking and stateful redaction of the redactable blockchain, we design a novel modification verification mechanism based on vector commitments. Finally, we provide detailed security analysis of the CHSTS scheme and integrate the proposed scheme into hyperledger fabric to evaluate the redactable blockchain through extensive experiments. The results demonstrate that our scheme incurs less computational overhead compared to the state-of-the-art chameleon hash schemes. Furthermore, our scheme maintains close efficiency compared to immutable blockchain, incurring negligible storage overhead.
Rvs Praveen, Aktalina Torogeldieva, B. C. Saravanan, Ajay Kumar · 6 authors
One way that technology is changing the legal profession is by increasing the role of neural networks in intellectual property rights (IPR). The present status of intellectual property rights might be drastically changed if neural networks were to be used to improve the efficiency, accuracy, and cost-effectiveness of copyright, patent, and trademark procedures. Neural networks have had a significant influence on several IP-related applications, such as patent analysis and search, copyright infringement detection, and trademark search. Included in the suggested method are model training, feature extraction, and pre-processing. The goal of pre-processing is to eliminate or replace irrelevant or noisy data from each tweet so that sentiment classification can proceed more effectively. Algorithms for sentiment categorization and information content analysis make up feature extraction. The training process always made use of the DGNN model. This cutting-edge approach outperforms CNN and GNN with an average accuracy of ${9 1. 4 5 \%}$.
Blockchain technology, the foundation of cryptocurrencies like Bitcoin, has utility beyond finance due to its decentralized and secure transactional nature. However, today's blockchain networks face the challenge of low transaction throughput due to block propagation delays. In this study, we propose a novel approach that divides large blocks into segments and leverages multi-origin pipelining for segment dissemination, thereby expediting block propagation. The scheme also integrates the use of a Bloom filter for lightweight segment integrity verification to prevent the reception of tampered segments. Simulation results reveal that our scheme outperforms Bitcoin's legacy approach, demonstrating significant improvement in propagation speed, particularly for large blocks, while maintaining a low fork rate.
The vast amounts of data produced by industrial IoT devices have recently attracted considerable attention across various scientific disciplines. While big data provides many benefits and applications, it also introduces several challenges that must be resolved to enhance service quality. Artificial intelligence (AI) and blockchain are recognized for their significant potential in strengthening big data security. This study addresses the security of lightweight devices that store large volumes of data but have limited memory and processing power. A lightweight framework for detecting zero-day attacks on resource-constrained yet data-intensive industrial devices was implemented. The performance of the proposed model was assessed using various metrics: Accuracy, Precision, Recall, F1-score, Evaluation time, Gas cost, Loss function, Transaction cost, and its performance compared to the state-of-the-art models. Federated learning (FL) simulation was conducted over 20 rounds, resulting in an overall global model learning accuracy of 97.7%, an F1-score of 97.1 %, a precision of 97.1 %, and a recall value of 97.7%, with a total evaluation time of 899.3 minutes. Additionally, all global model trainable parameters were efficiently deployed over the blockchain public network on the Ethereum smart contract. A security audit carried out showed an average score of 91 %.
S. Y. Xiao, Xiaoge Huang, Xuesong Deng, Bin Cao · 5 authors
To protect user privacy and data security, the integration of Federated Learning (FL) and blockchain has become an emerging research hotspot. However, the limited throughput and high communication complexity of traditional blockchains limit their application in large-scale FL tasks, and the synchronous traditional FL will also reduce the training efficiency. To address these issues, in this paper, we propose a Directed Acyclic Graph (DAG) blockchain-enabled generalized Federated Dropout (FD) learning strategy, which could improve the efficiency of FL while ensuring the model generalization. Specifically, the DAG maintained by multiple edge servers will guarantee the security and traceability of the data, and the Reputation-based Tips Selection Algorithm (RTSA) is proposed to reduce the blockchain consensus delay. Second, the semi-asynchronous training among Intelligent Devices (IDs) is adopted to improve the training efficiency, and a reputation-based FD technology is proposed to prevent overfitting of the model. In addition, a Hybrid Optimal Resource Allocation (HORA) algorithm is introduced to minimize the network delay. Finally, simulation results demonstrate the effectiveness and superiority of the proposed algorithms.
Enhancing data privacy security in medical data sharing is crucial for the informatization development in the healthcare sector. This paper proposes a healthcare data sharing scheme based on two-dimensional chaotic mapping and blockchain (2DCM-DS). Specifically, a new two-dimensional chaotic mapping is proposed, which demonstrates superior chaotic performance. Then, by incorporating biometric audio information as an identity credential and integrating it with the proposed two-dimensional chaotic mapping, we design a data encryption method that establishes a strongly coupled and bi-directionally verifiable data ownership relationship in healthcare data sharing. Finally, we employ blockchain as the underlying network and design corresponding smart contracts to support 2DCM-DS. This approach addresses potential issues of unauthorized access, malicious tampering, and single points of failure in centralized data sharing. Experimental results demonstrate that 2DCM-DS effectively protects data security under the specified attack models. The results validate the security and efficiency of the 2DCM-DS, proving its application potential in healthcare insurance data sharing scenarios.
As society increasingly relies on computers and automation, the challenge of developing secure applications, systems, and networks has become paramount. The complexity of modern networks and the proliferation of Internet of Things (IoT) devices have contributed to a surge in cyber threats facing individuals and organizations worldwide. Without effective collaboration, similar attacks can target multiple entities in rapid succession. While sharing cyber threat intelligence is often touted as a solution, privacy, trust, and traceability concerns persist. A novel distributed architecture is proposed to enhance IoT security to address these challenges. This solution relies on federated learning (FL) algorithms to establish a decentralized, autonomous system capable of detecting and characterizing attacks within a collaborative Cloud–SDN framework. Leveraging the strengths of Cloud computing and SDN, this architecture facilitates efficient and scalable data processing for IoT devices while safeguarding user privacy. By adopting FL, the model training process is decentralized, ensuring that sensitive data remains on the IoT devices, mitigating the risk of unauthorized access and data breaches.
Eranga Bandara, Peter Foytik, Sachin Shetty, Amin Hassanzadeh
The Metaverse is an integrated network of 3D virtual worlds accessible through a virtual reality headset. Its impact on data privacy and security is increasingly recognized as a major concern. There is a growing interest in developing a reference architecture that describes the four core aspects of its data: acquisition, storage, sharing, and interoperability. Establishing a secure data architecture is imperative to manage users' personal data and facilitate trusted AR/VR and AI/ML solutions within the Metaverse. This paper details a reference architecture empowered by Generative-AI, Blockchain, Federated Learning, and Non-Fungible Tokens (NFTs). Within this archi-tecture, various resource providers collaborate via the blockchain network. Handling personal user data and resource provider identities is executed through a Self-Sovereign Identity-enabled privacy-preserving framework. AR/NR devices in the Metaverse are represented as NFT tokens available for user purchase. Software updates and supply-chain verification for these devices are managed using a Software Bill of Materials (SBOM) and a Pipeline Bill of Materials (PBOM) verification system. Moreover, a custom-trained Llama2 LLM from Meta has been integrated to generate PBOMs for AR/NR devices' software updates, thereby preventing malware intrusions and data breaches. This Llama2-13B LLM has been quantized and fine-tuned using Qlora to ensure optimal performance on consumer-grade hardware. The provenance of AI/ML models used in the Metaverse is encapsu-lated as Model Card objects, allowing external parties to audit and verify them, thus mitigating adversarial learning attacks within these models. To the best of our knowledge, this is the very first research effort aimed at standardizing PBOM schemas and integrating Language Model algorithms for the generation of PBOMs. Additionally, a proposed mechanism facilitates different AI/ML providers in training their machine learning models using a privacy-preserving federated learning approach. Authorization of communications among AR/VR devices in the Metaverse is conducted through a Zero-Trust security-enabled rule engine. A system testbed has been implemented within a 5G environment, utilizing Ericsson new Radio with Open5GS 5G core.
Smart contracts, pivotal to blockchain technology, automate contract enforcement with precision and reliability but are plagued by security vulnerabilities that have led to significant financial losses. Traditional methods like static analysis and fuzzy testing, though foundational, typically fail to grasp the complex logic of smart contract code, resulting in poor adaptability to the evolving landscape of blockchain applications. To address these challenges, this paper introduces an advanced Graph Neural Network (GNN) approach tailored for smart contract vulnerability detection on the VNT blockchain platform. Our methodology leverages the inherent structural and semantic relationships within contract code, transforming it into a graph representation for deeper learning. The enhanced GNN model effectively captures intricate patterns and dependencies that traditional methods overlook, significantly improving detection accuracy and efficiency. Experimental results demonstrate that our approach outperforms existing techniques, offering a promising avenue for both refining smart contract security analyses and guiding future development practices. We further contribute to the field by providing a robust dataset of smart contracts, fostering further research and application enhancements. Experimental results demonstrate that the proposed method not only advances the security of smart contract in VNT but also establishes a new benchmark for the application of deep learning in blockchain.
Blockchain, as a decentralized, secure, programmable, traceable, and tamper-resistant distributed ledger technology, has witnessed rapid development in various fields in recent years. This paper addresses the need for rapid data retrieval on blockchain and proposes a block construction and retrieval algorithm based on hybrid indexing. The algorithm aims to alter the underlying structure of blocks by utilizing data structures such as Merkle trees, linked lists, and hashes to facilitate data retrieval. Building upon this, block construction and retrieval algorithms are introduced to ensure efficient retrieval of corresponding transactions, maintaining low time complexity.
Xuanxia Yao, Jinyuan Zhou, Xiaojiang Du, Shurong Zhang
Nowadays, we are living in an open network environment with varieties of smart devices, which makes individual privacy face unprecedented threats. For one thing, a plenty of sensitive information may be gathered without the owner’s knowledge. For the other, the Internet of Things (IoT)-based services and various intelligent applications require a large amount of perceptual data. And in practice, these data are usually encrypted and stored in storage providers like cloud for security and cost saving. To fully harness the productivity value of data and protect privacy, ciphertext-policy attribute-based encryption (CP-ABE) is widely used. Nevertheless, most existing CP-ABE schemes cannot work well for IoT because of the heavy overhead and the open and distributed environment. To lower the cost, a lightweight CP-ABE scheme without pairing is proposed and proved in the set-selective mode. Both the theoretical analysis and experiments show its advantages in computation, communication, and storage overhead. For flexible access control in IoT, we attempt to employ the masked authenticated message (MAM) mechanism of the IOTA to manage authorization for our CP-ABE scheme. Comparisons with similar schemes show that it can overcome the low throughput and monetary cost in other distributed ledger-based access control schemes.
In this paper, we investigate the secure task offloading and computation resource allocation issues in a consortium blockchain-enabled multi-access edge computing (MEC) system. Specifically, edge servers and a cloud center provides user equipments (UEs) with augmented computing power for task processing, while consortium blockchain can provide trust and secure guarantee to UEs in task offloading. Within the MEC system, we intend to minimize the task processing cost of all UEs by jointly optimizing the binary task offloading decision and the computation resource block allocation. Meanwhile, in the blockchain system, we first enhance the consensus procedure by proposing an improved practical Byzantine fault tolerance (IPBFT) consensus algorithm, and then conduct consensus committee selection, thus to minimize consensus delay and fail ratio. The two systems are jointly optimized, subjecting to the computation power of edge nodes, the node number limitation of IPBFT, the task processing and blockchain consensus delay, etc. To address the problem effectively, we reform it into a Markov decision process (MDP) and use proximal policy optimization (PPO) to dynamically learn the optimal joint solution. Simulation results demonstrate that our proposed algorithm converges fast, and performs well in total reward maximization, and UEs’ cost, consensus delay and fail ratio minimization.
In recent years, the confluence of federated learning and model parallelism has revolutionized the landscape of deep learning on distributed systems, significantly enhancing efficiency and scalability. Federated learning, a decentralized approach, enables multiple edge devices to collaboratively train a model without sharing their data, thereby preserving privacy and reducing latency. Model parallelism, on the other hand, divides a large model across several devices, allowing for simultaneous computation and faster processing. By synergizing these two paradigms, researchers have developed innovative frameworks that leverage the strengths of both approaches, achieving superior performance and resource utilization. This hybrid strategy addresses the limitations of traditional centralized training, offering a robust solution for large-scale, privacy-sensitive applications.The integration of federated learning and model parallelism not only optimizes computational resources but also mitigates communication bottlenecks inherent in distributed systems. This amalgamation is particularly advantageous for deep learning tasks involving vast datasets and complex models, as it distributes the computational load and enhances fault tolerance. Moreover, this approach supports continuous learning from distributed data sources, facilitating real-time updates and adaptability. As a result, turbocharged AI systems leveraging these technologies can efficiently handle the growing demands of contemporary deep learning applications, paving the way for advancements in fields such as healthcare, finance, and autonomous systems.
K. Deepthika, G. Shobana, Kumbam Venkat Reddy, S Srimathi · 6 authors
The collection of medical data encompasses a variety of patient records that hold significant value for ongoing treatment and future research works. To ensure the privacy of the data, it is imperative to store and share it securely. Utilizing blockchain technology in managing healthcare data is prevalent due to its decentralized nature and ability to provide tamper-proof security measures. In healthcare's dynamic and ever-changing realm, the importance of securely sharing sensitive health data and managing consent effectively cannot be overstated. These factors are crucial in safeguarding patient privacy and promoting collaborative research efforts. This study aims to investigate the potential integration of blockchain technology and Long Short-Term Memory (LSTM) deep learning models to develop a comprehensive framework that ensures secure health data sharing and effective consent management. Integrating blockchain technology's decentralized and immutable ledger with the sequential learning capabilities of LSTM presents a promising approach to tackle the various obstacles related to data integrity, provenance, and patient-centric consent within healthcare ecosystems. The proposed system aims to improve the security and transparency of health data transactions while enabling dynamic consent management. This empowers individuals to have more control over their data. In this study, aims to assess the effectiveness of the blockchain-integrated LSTM model in ensuring health data security. Additionally, the investigated model facilitates smooth and privacy-preserving collaboration among various healthcare stakeholders. The experiments involved utilizing two publicly available data sources, CICIDS-2017 and NSL-KDD. These experiments evaluated the proposed model's performance compared to existing state-of-the-art approaches within non-blockchain and blockchain settings. The results demonstrated that the proposed model exhibited superior performance across both datasets, achieving an accuracy rate of approximately 99%.
Brain Tumor Detection and Classification
Blockchain Technology Applications and Security
Artificial Intelligence in Healthcare and Education
Various deep learning techniques, including blockchain-based approaches, have been explored to unlock the potential of edge data processing and resultant intelligence. However, existing studies often overlook the resource requirements of blockchain consensus processing in typical Internet of Things (IoT) edge network settings. This paper presents our FLCoin approach. Specifically, we propose a novel committee-based method for consensus processing in which committee members are elected via the FL process. Additionally, we employed a two-layer blockchain architecture for federated learning (FL) processing to facilitate the seamless integration of blockchain and FL techniques. Our analysis reveals that the communication overhead remains stable as the network size increases, ensuring the scalability of our blockchain-based FL system. To assess the performance of the proposed method, experiments were conducted using the MNIST dataset to train a standard five-layer CNN model. Our evaluation demonstrated the efficiency of FLCoin. With an increasing number of nodes participating in the model training, the consensus latency remained below 3 s, resulting in a low total training time. Notably, compared with a blockchain-based FL system utilizing PBFT as the consensus protocol, our approach achieved a 90% improvement in communication overhead and a 35% reduction in training time cost. Our approach ensures an efficient and scalable solution, enabling the integration of blockchain and FL into IoT edge networks. The proposed architecture provides a solid foundation for building intelligent IoT services.
More and more in healthcare is blockchain technology applied for safe and open data storage. Still, it is understudied how deeply regression analysis combined with nonlinear dynamics into distributed ledger systems performs. This kind of approach may help to increase data transfer efficiency and help storage management in blockchain systems. Data speed and storage efficiency restrictions make current blockchain systems difficult to handle for large amounts of healthcare data. Conventional methods find poor data retrieval and transfer due to the great complexity and nonlinear characteristics of healthcare data. Combining nonlinear dynamics with deep regression analysis, this paper proposes a fresh approach for maximizing data transfer and storage in blockchain systems. Inspired by nonlinear dynamics ideas, a deep regression model aimed at maximizing block storage and forecast data transmission requirements was assessed on a simulated healthcare dataset using a distributed ledger system with 1,000 blocks and a 500 GB total dataset size. Performance criteria covered transmission efficiency and storage consumption. The proposed technique improved data transmission efficiency by thirty percent over current techniques. Another clear improvement was using storage; block size needs fell 25%. The best model, according to numerical research, lowered an average transmission time from 120 to 84 minutes and storage overhead from 200 to 150 GB.
Rongping Lin, Fan Wang, Shan Luo, Xiong Wang · 5 authors
Federated Learning (FL) is a distributed machine learning method that ensures the privacy and security of participants’ data by avoiding direct data upload to a central node for training. However, the traditional FL typically applies a star structure with cloud servers as the central aggregator for the model parameters from different terminals, leading to problems such as central failure, malicious tampering and malicious participants, resulting in training errors or system crashes. To address these issues, a permissioned blockchain is used to build a secure and reliable data-sharing platform among participating terminals, replacing the central aggregator in the traditional FL called blockchain-based federated learning. However, the block generation method of the blockchain system may introduce significant latency in the federated learning where distributed model parameters upload randomly, resulting in low efficiency of the federated learning. To overcome this, we propose a block generation strategy that groups terminals and generates a block for each group, which minimizes the latency of a single round of federated learning, and an optimal block generation algorithm that considers data distribution, terminal resources, and network resources is provided. The analysis shows that the proposed algorithm can effectively obtain the optimal solution of block generation to minimize the authentication time, and we conduct extensive experiments that demonstrate the time efficiency of the proposed algorithm.
In the era of cloud computing, guaranteeing the safety and effectiveness of data management is of utmost importance. This investigation presents a novel approach that amalgamates the sharding concept, encryption, zero-knowledge proofs (zkp), and blockchain technology for secure data retrieval and data access control to improve data security, efficiency in cloud storage and migration. Further, we utilize user-specific digital wallets for secure encryption keys in order to encrypt the file before storing into the cloud. As Large files (greater than 50 MB) or Big data files (greater than 1 TB) require greater computational complexity, we leverage the sharding concept to enhance both space and time complexity in cloud storage. Hence, the large files are divided into shards and stored in different database servers. We also employ a blockchain smart contract to enhance secure retrieval of the file and also a secure access method, which ensures the privacy of the user. The zk-snark protocol is utilized to ensure the safe transfer of data between different cloud services. By utilizing this approach, data privacy is preserved, as only the proof of the data’s authenticity is shared with the verifier at the destination cloud, rather than the actual data themselves. The suggested method tackles important concerns related to data protection, privacy, and efficient resource utilization in cloud computing settings by ensuring it meets all the cloud policies required to store data. Since the environment maintains the privacy of the user data and the raw data of the user is not stored anywhere, the entire environment is set up as a Zero trust model.
With the development of smart grid, the introduction of blockchain technology provides a novel idea for secure power data sharing. The existing blockchain-based data aggregation schemes generally rely on a unique leader node to perform verification algorithms, but there may be a lazy leader node not performing aggregation data verification to save computation costs. In addition, in the existing verification mechanism, light nodes need to perform the same verification operations as the leader node, which results in resource-constrained light nodes being unable to bear. In this paper, we propose an efficient blockchain-based data aggregation scheme with privacy-preserving on the smart grid, called EC-ASPG, which implements a supervised mechanism for the lazy leader node, enhancing the security of the system. Furthermore, we propose a separable consensus verification mechanism, which can prevent other light nodes from performing duplicate verification operations like the leader node, effectively improving the efficiency of consensus verification. Finally, we present a formal security proof and comprehensive performance evaluations. The results show that our scheme is secure and outperforms the compared schemes in terms of performance analysis.
In contemporary society, management of physical documents such as educational certificates, identity proofs, vehicle registrations, and marriage certificates is an integral part of daily life. However, in present online world, there is a pressing need for digital transformation and the management of these documents. One significant challenge associated with this transformation is the susceptibility of original documents to replication or duplication. This vulner- ability is particularly concerning in the case of educational certificates, where fraud is prevalent. Fraudulent activities in the education sector can influence the proliferation of counterfeit educational and skill certificates, posing serious risks to society. For instance, individuals holding fraudulent degrees in professions such as engineering, medicine, law, and pharmacy may lack genuine competence, thereby posing substantial societal harm. To address the issue of certificate oversight and deter forgery, various approaches have been employed. Traditional methods typically involve the use of centralized databases or web servers for certificate storage, which introduces vulnerabilities because they represent single points of failure that leads to forgery and information loss. An optimal solution lies in the adoption of a Blockchain system that leverages a decentralized database structure to enhance data storage capacity and security. Blockchain technology has demonstrated disruptive potential and in- novative capabilities across multiple sectors because of its decentralized, transparent, and secure attributes. Its impact spans various domains, including banking, supply chain management, healthcare, education, and finance. Notably, in the education sector, Blockchain technology holds promise in enhancing security, transparency, and efficiency across different educational processes. In this study, we explore existing Blockchain oriented certificate management systems, critically analyze their limitations, and propose a novel hybrid educational certificate management model. The proposed model integrates Hyperledger Fabric, IoT, and 2D Barcode to develop a robust and secure framework for managing educational certificates.
With the vigorous development of the blockchain industry, cross-chain transactions can effectively solve the problem of “islands of value” caused by the inability to interact between different chains. However, security risks in reputation management caused by cross-chain transactions implemented through notary solutions have always existed. Consequently, this paper proposes a blockchain cross-chain transaction method based on decentralized dynamic reputation value assessment. The notary election phase addresses the issue of the continually changing behaviour of notaries in actual transactions by designing a dynamic evaluation window mechanism based on an RNN. Moreover, a reputation-rating decay mechanism is introduced to avoid the problem of reputation value recovery caused by malicious notaries being inactive for a long time. Relative to alternative reputation assessment models, the proposed method offers a thorough evaluation of user behavior and effectively identifies malicious activities in real-time. Finally, the method was tested by deploying it on the Ethereum blockchain. Our approach offers more dynamic settings for window parameters, adapting to changes in notary behavior and reducing the number of detections within the same timeframe by approximately 59.14%. The weight factor settings are also optimized, allowing for adjustments based on specific situations to achieve accurate reputation values. Overall, this method not only enhances the security of cross-chain transactions but also reduces operational costs by 53.3% compared to traditional technologies.