Ranking algorithms in traditional search engines are powered by enormous training data sets that are meticulously engineered and curated by a centralized entity. Decentralized peer-to-peer (p2p) networks such as torrenting applications and Web3 protocols deliberately eschew centralized databases and computational architectures when designing services and features. As such, robust search-and-rank algorithms designed for such domains must be engineered specifically for decentralized networks, and must be lightweight enough to operate on consumer-grade personal devices such as a smartphone or laptop computer. We introduce G-Rank, an unsupervised ranking algorithm designed exclusively for decentralized networks. We demonstrate that accurate, relevant ranking results can be achieved in fully decentralized networks without any centralized data aggregation, feature engineering, or model training. Furthermore, we show that such results are obtainable with minimal data preprocessing and computational overhead, and can still return highly relevant results even when a user's device is disconnected from the network. G-Rank is highly modular in design, is not limited to categorical data, and can be implemented in a variety of domains with minimal modification. The results herein show that unsupervised ranking models designed for decentralized p2p networks are not only viable, but worthy of further research.
Asif Ali Laghari, Abdullah Ayub Khan, Reem Alkanhel, Hela Elmannai ¡ 5 authors
The vast enhancement in the development of the Internet of Vehicles (IoV) is due to the impact of the distributed emerging technology and topology of the industrial IoV. It has created a new paradigm, such as the security-related resource constraints of Industry 5.0. A new revolution and dimension in the IoV popup raise various critical challenges in the existing information preservation, especially in node transactions and communication, transmission, trust and privacy, and security-protection-related problems, which have been analyzed. These aspects pose serious problems for the industry to provide vehicular-related data integrity, availability, information exchange reliability, provenance, and trustworthiness for the overall activities and service delivery prospects against the increasing number of multiple transactions. In addition, there has been a lot of research interest that intersects with blockchain and Internet of Vehicles association. In this regard, the inadequate performance of the Internet of Vehicles and connected nodes and the high resource requirements of the consortium blockchain ledger have not yet been tackled with a complete solution. The introduction of the NuCypher Re-encryption infrastructure, hashing tree and allocation, and blockchain proof-of-work require more computational power as well. This paper contributes in two different folds. First, it proposes a blockchain sawtooth-enabled modular architecture for protected, secure, and trusted execution, service delivery, and acknowledgment with immutable ledger storage and security and peer-to-peer (P2P) network on-chain and off-chain inter-communication for vehicular activities. Secondly, we design and create a smart contract-enabled data structure in order to provide smooth industrial node streamlined transactions and broadcast content. Substantially, we develop and deploy a hyperledger sawtooth-aware customized consensus for multiple proof-of-work investigations. For validation purposes, we simulate the exchange of information and related details between connected devices on the IoV. The simulation results show that the proposed architecture of BIoV reduces the cost of computational power down to 37.21% and the robust node generation and exchange up to 56.33%. Therefore, only 41.93% and 47.31% of the Internet of Vehicles-related resources and network constraints are kept and used, respectively.
In recent years, federated learning has been able to provide an effective solution for data privacy protection, so it has been widely used in financial, medical, and other fields. However, traditional federated learning still suffers from single-point server failure, which is a frequent issue from the centralized server for global model aggregation. Additionally, it also lacks an incentive mechanism, which leads to the insufficient contribution of local devices to global model training. In this paper, we propose a blockchain-based decentralized federated learning method, named BD-FL, to solve these problems. BD-FL combines blockchain and edge computing techniques to build a decentralized federated learning system. An incentive mechanism is introduced to motivate local devices to actively participate in federated learning model training. In order to minimize the cost of model training, BD-FL designs a preference-based stable matching algorithm to bind local devices with appropriate edge servers, which can reduce communication overhead. In addition, we propose a reputation-based practical Byzantine fault tolerance (R-PBFT) algorithm to optimize the consensus process of global model training in the blockchain. Experiment results show that BD-FL effectively reduces the model training time by up to 34.9% compared with several baseline federated learning methods. The R-PBFT algorithm can improve the training efficiency of BD-FL by 12.2%.
Over the last few decades, the healthcare industry has continuously grown, with hundreds of thousands of patients obtaining treatment remotely using smart devices. Data security becomes a prime concern with such a massive increase in the number of patients. Numerous attacks on healthcare data have recently been identified that can put the patientâs identity at stake. For example, the private data of millions of patients have been published online, posing a severe risk to patientsâ data privacy. However, with the advent of Industry 4.0, medical practitioners can digitally assess the patientâs condition and administer prompt prescriptions. However, wearable devices are also vulnerable to numerous security threats, such as session hijacking, data manipulation, and spoofing attacks. Attackers can tamper with the patientâs wearable device and relays the tampered data to the concerned doctor. This can put the patientâs life at high risk. Since blockchain is a transparent and immutable decentralized system, it can be utilized for securely storing patientâs wearable data. Artificial Intelligence (AI), on the other hand, utilizes different machine learning techniques to classify malicious data from an oncoming stream of patientâs wearable data. An amalgamation of these two technologies would make the possibility of tampering the patientâs data extremely difficult. To mitigate the aforementioned issues, this paper proposes a blockchain and AI-envisioned secure and trusted framework (HEART). Here, Long-Short Term Model (LSTM) is used to classify wearable devices as malicious or non-malicious. Then, we design a smart contract that allows only of those patientsâ data having a wearable device to be classified as non-malicious to the public blockchain network. This information is then accessible to all involved in the patientâs care. We then evaluate the HEARTâs performance considering various evaluation metrics such as accuracy, recall, precision, scalability, and network latency. On the training and testing sets, the model achieves accuracies of 93% and 92.92%, respectively.
As the number of smart cars grows rapidly, vehicular crowdsensing (VCS) is gradually becoming popular. In a VCS infrastructure, sensing devices and computing units hold on smart cars as well as cloud servers form an IoT-edge-cloud continuum to perform real-time sensing tasks. In order to encourage the smart cars to participate in the real-time VCS process, blockchain technology can be combined with VCS to provide an automated incentive for VCS data trading without relying on trusted third parties. However, directly using blockchain to enforce the VCS data trading process incurs expensive service fees and participants still can conduct various misbehavior. In this article, we propose a secure blockchain-based data trading system for VCS named BTT system to address the above issues. In particular, we first integrate the blockchain-based data trading process with a lightweight privacy-preserving truth discovery algorithm to ensure the accuracy of sensing data while preserving data privacy. We then propose a gas-aware optimization mechanism to minimize the gas consumption of the data trading process. Finally, we carefully design a distributed judgment mechanism to regulate all participants to behave correctly in the data trading process. To demonstrate the practicability of our design, we implement a prototype of the BTT system deployed on an Ethereum test network and conduct extensive simulations.
The adoption of modern health records is growing more mature, yet security issues always accompany it. Interplanetary file system (IPFS) and blockchain are developing technologies with decentralization, distributed fault tolerance, and trustworthiness. Using IPFS and blockchain technology to tackle medical health record data security issues is a very promising trend, and it is presently being utilized to secure medical health record data security. This article first explains the idea of IPFS and highlights the classification of existing IPFS and blockchain techniques before briefly discussing distributed ledger to tackle the existing medical health record data security challenges and faults. Finally, to preserve medical health records, a new medical health record storage architectural model based on IPFS and blockchain technologies is presented.
Industrial Internet of Things (IIoT) opens up a challenging research area towards improving secure data sharing which currently has several limitations. Primarily, the lack of inbuilt guarantees of honest behavior of participating, such as end-users or cloud behaving maliciously may result in disputes. Given such challenges, we propose a fair, accountable, and secure data sharing scheme, $\textit{FairShare}$ for IIoT. In this scheme, data collected from IoT devices are processed and stored in cloud servers with intermediate fog nodes facilitating computation. Authorized clients can access this data against some fee to make strategic decisions for improving the operational services of the IIoT system. By enabling blockchain, $\textit{FairShare}$ prevents fraudulent activities and thereby achieves fairness such that each party gets their rightful outcome in terms of data or penalty/rewards while simultaneously ensuring accountability of the services provided by the parties. Additionally, smart contracts are designed to act as a mediator during any dispute by enforcing payment settlement. Further, security and privacy of data are ensured by suitably applying cryptographic techniques like proxy re-encryption. We prove $\textit{FairShare}$ to be secure as long as at least one of the parties is honest. We validate $\textit{FairShare}$ with a theoretical overhead analysis. We also build a prototype in Ethereum to estimate performance and justify comparable results with a state-of-the-art scheme both via simulation and a realistic testbed setup. We observe an additional communication overhead of 256 bytes and a cost of deployment of 1.01 USD in Ethereum which are constant irrespective of file size.
In the scenario of highly mobile nodes, applying blockchain not only needs to ensure high performance and security but also needs to consider the low stability of consensus nodes. We introduce a novel framework to reduce the negative impact of low-stable consensus nodes. In addition, we have developed an intelligent algorithm for selecting the optimal number of Mobile Consensus Nodes (MCNs) considering various parameters including Stability of Node (SoN). The results demonstrate that the proposed scheme improves the average reputation and stability of consensus nodes by 6.8% and 17.5%, respectively while reducing the average message counts by 33.9%.
The amount of sensitive information that service providers handle about their users has become a concerning fact in many use cases, where users have no other option but to trust that those companies will not misuse their personal information. To solve that, Self-Sovereign Identity (SSI) systems have become a hot topic of research in recent years: SSI systems allow users to manage their identities transparently. Recent solutions represent the rights of users to use services as Non-Fungible Tokens (NFTs) stored on Blockchains, and users prove possession of these rights using Zero-Knowledge Proofs (ZKPs). However, even when ZKPs do not leak any information about the rights, the NFTs are stored as public values linked to known accounts, and thus, they can be traced. In this paper, we design a native privacy-preserving NFT model for the Dusk Network Blockchain, and on top of it, we deploy Citadel: our novel full-privacy-preserving SSI system, where the rights of the users are privately stored on the Dusk Network Blockchain, and users can prove their ownership in a fully private manner.
The advent of blockchain technology in the development and design of smart internet of things (IoT) systems offers the opportunity to secure and transfer data flow, preserve its integrity, and provide transparent mechanisms for its management. Blockchain has actually attracted applications in vital fields because it provides many advantages over centralized database such as traceability, confidentiality, availability and trust. A private network offers the most secure and peer-restricted environment for big data flow, specifically in IoT ecosystems. An integrated blockchain-IoT ecosystem in which three Raspberry Pi 4 nodes communicate and interact in a closed loop to control smart applications via an Ethereum platform in a secure and an efficiently emulated environment is piloted. The proposed blockchain of things (BCoT) ecosystem adds a new layer to the physical, network and application layers of a typical IoT architecture. The concept of a fully decentralized private Ethereum BCoT network may find applications in several fields that call for the removal of single-point of failure and ensures data integrity and transparency.
User-centric data sharing is essential to encourage citizens' active participation in the digital economy. One key to smart cities, a form of the digital economy, is the promotion of public use of citizen data. Nevertheless, it is not easy to utilize data without citizensâ consent. In this study, we took a technological approach to these issues. User-managed access (UMA) is a well-known framework for delegating resource access rights to others on the Internet. In UMA, authorization mechanisms are designed to be centralized so that resource owners can centrally manage access rights for various resources stored in different domains. However, the lack of transparency in the authorization mechanism is a barrier to its implementation in large-scale systems such as smart cities. In this study, we developed a blockchain-based cross-domain authorization architecture that enables a resource-sharing ecosystem in which organizations that wish to utilize data can freely trade with each other. The proposed architecture solves the transparency problem that conventional authorization systems have had by designing the authorization mechanism on blockchain technology. We implemented the proposed architecture as smart contracts and evaluated its processing performance. The resultant time required for delegating access rights and accessing resources was less than 500 âms. Furthermore, we found that the fluctuation in the processing time overhead was small. Based on these results, we concluded that performance degradation with the proposed architecture is minor.
Sarra Namane, Marwa Ahmim, Aron Kondoro, Imed Ben Dhaou
In the era of the Fourth Industrial Revolution, cybercriminals are targeting critical infrastructures such as traffic light systems and smart grids. A major concern is the security of such systems, which can be broken down into a number of categories, such as the authentication of data collection devices, secure data transmission, and use of the data by authorized and authenticated parties. The majority of research studies in the literature have largely focused on data integrity and user authentication. So far, no published work has addressed the security of a traffic light system from data collection to data access. Furthermore, it is evident that the conventional cloud computing architecture is incapable of analyzing and managing the massive amount of generated data. As a result, the fog computing paradigm combined with blockchain technology may be the best way to ensure data privacy in a decentralized manner while reducing overheads, latency, and maintaining security. This paper presents a blockchain-based authentication scheme named VDAS using the fog computing paradigm. The formal and informal verifications of the proposed solution are presented. The evaluation of the proposed scheme VDAS showed that it has low communication and computation costs compared to existing lightweight authentication techniques.
Abdulla All Noman, Mustafizur Rahaman, Tahmid Hasan Pranto, Rashedur M. Rahman
The scarcity and diversity of medical data have made it challenging to build an accurate global classification model in the healthcare sector. The prime reason is privacy concerns and legal obstacles which limit data-sharing scope among institutions in healthcare. On the other hand, data from a single source is hardly sufficient to develop a universal diagnosis model. While federated learning is a potential solution to privacy and data diversity concerns (allows distributed model training), an apt aggregation process for multi-class and heterogenous medical data is still at the outset. This study aims to propose a federated learning mechanism that can effectively learn from multi-class and heterogenous respiratory medical data. The proposed system trains and aggregates the local model by leveraging blockchain technology, ensuring privacy. While aggregating the local models, we introduced the weight manipulation technique that, unlike any other studies, uses the local model test accuracy as the principal parameter. The resulting metric scores show that learning from diverse and heterogenous data, the performance of the proposed federated model is analogous to a single-source model (learning from single source data). Using the novel aggregation technique, the highest testing accuracy of 88.10% has been achieved for five classes, compared to the less complex single source model, which achieved 88.60% testing accuracy. A similar trend has been observed for models with three and four classes. For developing better synergy among organizations, this study introduces an incentive mechanism for the contributing institution while the blockchain stores the records to make the system transparent and trustworthy. The proposed mechanism has been implemented using a web system, which demonstrates how the weight manipulation technique can effectively learn from heterogeneous and multi-sourced data while preserving privacy.
Marc Jayson Baucas, Petros Spachos, Konstantinos N. Plataniotis
Over the years, the popularity and usage of wearable Internet of Things (IoT) devices in several healthcare services are increased. Among the services that benefit from the usage of such devices is predictive analysis, which can improve early diagnosis in e-health. However, due to the limitations of wearable IoT devices, challenges in data privacy, service integrity, and network structure adaptability arose. To address these concerns, we propose a platform using federated learning and private blockchain technology within a fog-IoT network. These technologies have privacy-preserving features securing data within the network. We utilized the fog-IoT networkâs distributive structure to create an adaptive network for wearable IoT devices. We designed a testbed to examine the proposed platformâs ability to preserve the integrity of a classifier. According to experimental results, the introduced implementation can effectively preserve a patientâs privacy and a predictive serviceâs integrity. We further investigated the contributions of other technologies to the security and adaptability of the IoT network. Overall, we proved the feasibility of our platform in addressing significant security and privacy challenges of wearable IoT devices in predictive healthcare through analysis, simulation, and experimentation.
(1) Background: As Patient-reported outcome measures face challenges with low response rate on surveys, different incentive mechanism have been proposed to achieve a higher response rate. However, it seems that monetary incentives are the only mechanism with proven effect. Nevertheless, it is less likely to be used than other mechanisms due to the monetary cost. (2) Methods: In this research work, a cryptographic scheme for rewarding patients with cryptographic tokens is developed and implemented on the Ethereum test network. (3) Results: The model is able to distribute decentralised tokens to patients who complete the PROMs in a fair, private, decentralised approach. The token can be further used by patients to exchange more healthcare services, encouraging more patients to participate in PROMs. At the same time, an IER detection method is built to improve the quality of PROMs, avoiding the healthcare provider paying for meaningless PROMs from patients who barely participate for incentives. (4) Conclusions: This work provides an privacy-preserving incentive model to increase the response rate for PROMs surveys. Our model prevents patients providing invalid responses to gain rewards.
Abstract Blockchain technology (BT) allows market participants to keep track of digital transactions without central recordkeeping. The features of blockchain, including decentralization, persistency, and attack resistance, allow data security and privacy. Machine learning (ML) involves the analytical platform on a massive amount of data to provide precise decisions. Since data reliability, integration, and data security are crucial in machine learning, the emergence of blockchain technology and machine learning has become a unique, most disruptive, and trending research in the last few years, achieving comparable and precise performance. The combination of blockchain and machine learning (BTâML) has been applied across different applications to assist decision-makers in retrieving valuable data insights while preserving privacy and integration. This paper summarizes the state-of-the-art research in combing BT and ML in e-commerce and other various applications, including healthcare, smart transportation, and the Internet of Things (IoT). The challenges and benefits of integrating machine learning and blockchain technologies are outlined in the paper. We also discuss the advantages and limitations of current algorithms in the BTâML integration. This paper provides a roadmap for researchers to pave the way for current and future research directions in combing the BT and ML research areas.
Hung Du, Srikanth Thudumu, Sankhya Singh, Scott D. Barnett ¡ 7 authors
The rapid growth of both the Industrial Internet of Things (IIoT) and Artificial Intelligence (AI) results in a high demand for AI applications in devices. To achieve high levels of accuracy, AI applications typically require a large amount of annotated data. Accessing such data is challenging in various applications such as healthcare, finance and information security. Federated learning (FL) is one of the strategies that was proposed to overcome this challenge. Specifically, FL enables the AI model in the centralized system to be trained without any prior knowledge of the information on the devices. Recent FLs have the disadvantage that they are dependent upon a centralized system, and thus are susceptible to single points of failure. This paper proposes a strategy that employs FL in a decentralized environment where devices can communicate with each other to increase the accuracy of the AI model in each device. Furthermore, we evaluate the proposed strategy in the image classification task with the ResNet50 architecture and the CIFAR-10 dataset. The evaluation shows that the ResNet50 model trained in the decentralized environment can achieve comparable results to the model trained in the centralized environment.
Abstract With the rapid increment of the demand for data sharing among parties, data is considered a cornerstone component to provide value in the big data environment. Concerns regarding sharing data security have impeded the development of crossâdomain data interaction. Therefore, an access control model for data security sharing crossâdomain is proposed, FabricâABAC, that is based on Hyperledger Fabric and Attributeâbased Access Control (ABAC). In order to solve the data security challenges caused by a trusted central organization implementation, a distributed environment is constructed that consists of stakeholders among parties. The unified attribute model is designed for multiâenvironment combined with smart contracts. FabricâABAC realizes multiâlevel, fineâgrained, and auditable access control, enabling data security through automatic permission verification. Considering the ledger is visible to all participants in consortium blockchain, it is necessary to protect the confidentiality of sensitive data. Thus, Proxy ReâEncryption (PRE), which is implemented by smart contracts, is adopted in the scheme to realize the ciphertext interaction without the third party. The security of PRE and the access control model used in FabricâABAC is discussed to show that a secure environment for data sharing is provided. Moreover, the completeness of the implementation and effectiveness of the system performance in the multiâdomain environment is demonstrated in the experimental results.
ML-based applications already play an important role in factories in areas such as visual quality inspection, process optimization, and maintenance prediction and will become even more important in the future. For ML to be used in an industrial setting in a safe and effective way, the different steps needed to use ML must be put together in an ML pipeline. The development of ML pipelines is usually conducted by several and changing external stakeholders because they are very complex constructs, and confidence in their work is not always clear. Thus, end-to-end trust in the ML pipeline is not granted automatically. This is because the components and processes in ML pipelines are not transparent. This can also cause problems with certification in areas where safety is very important, such as the medical field, where procedures and their results must be recorded in detail. In addition, there are security challenges, such as attacks on the model and the ML pipeline, that are difficult to detect. This paper provides an overview of ML security challenges that can arise in production environments and presents a framework on how to address data security and transparency in ML pipelines. The framework is presented using visual quality inspection as an example. The presented framework provides: (a) a tamper-proof data history, which achieves accountability and supports quality audits; (b) an increase in trust by protocol for the used ML pipeline, by rating the experts and entities involved in the ML pipeline and certifying legitimacy for participation; and (c) certification of the pipeline infrastructure, the ML model, data collection, and labelling. After describing the details of the new approach, the mitigation of the previously described security attacks will be demonstrated, and a conclusion will be drawn.
Damiano Di Francesco Maesa, Andrea Lisi, Paolo Mori, Laura Ricci ¡ 5 authors
Recent years have witnessed, especially in Europe, a shift aimed at bringing users back at the center of digital systems. This has driven innovation towards the affirmation of decentralized systems, in line with the Self Sovereign Identity paradigm. User control over the consumption and disclosure of their data is a key topic of such drive. In this paper we show how it is possible to apply this increasingly popular concept to a traditionally centralized and opaque digital process: Access Control systems. To this aim we expand the XACML standard for Attribute Based Access Control systems with the novel concept of private attributes, i.e. attributes whose values should not be disclosed while still contributing to a policy evaluation result after user consent. Basing our proposal on blockchain systems, we show how to leverage smart contracts and zero knowledge proofs to allow for transparent policies evaluation without disclosing the value of such sensible attributes. Beside formalizing our goals, presenting the system architecture, and discussing its advantages and drawbacks with respect to the traditional model, we provide a reference example to show our proposal innovative capabilities and provide a prototype experimental evaluation to prove its feasibility.
Xin Liu, Xiaofen Tu, Dan Luo, Gang Xu ¡ 6 authors
In recent years, with the development of information security, secure multi-party computation has gradually become a research hotspot in the field of privacy protection. The intersection and union computation of graphs is an important branch of secure computing geometry. At present, the intersection and union of graphs are almost designed under the semi-honest model, and few solutions are proposed under the malicious model. However, the solution under the malicious model is more secure and has important theoretical and practical significance. In this paper, the possible malicious behaviors of computing the intersection and union of graphs are analyzed. Using the Lifted-ElGamal threshold cryptosystem and zero-knowledge proof method, the secure multi-party computation algorithm of graphsâ intersection and union under the malicious model is designed. The real/ideal model paradigm is used to prove the security of the algorithm, the efficiency of the algorithm is analyzed in detail, and the feasibility is verified through experiment.
Internet of Vehicles (IoV) has become an indispensable technology to bridge vehicles, persons, and infrastructures and is promising to make our cities smarter and more connected. It enables vehicles to exchange vehicular data (e.g., GPS, sensors, and brakes) with different entities nearby. However, sharing these vehicular data over the air raises concerns about identity privacy leakage. Besides, the centralized architecture adopted in existing IoV systems is fragile to single point-of-failure and malicious attacks. With the emergence of blockchain technology, there is the chance to solve these problems due to its features of being tamper-proof, traceability, and decentralization. In this article, we propose a privacy-preserving vehicular data sharing framework based on blockchain. In particular, we design an anonymous and auditable data sharing scheme using Zero-Knowledge Proof (ZKP) technology so as to protect the identity privacy of vehicles while preserving the vehicular data auditability for Trusted Authorities (TAs). In response to high mobility of vehicles, we design an efficient multi-sharding protocol to decrease blockchain communication costs without compromising the blockchain security. We implement a prototype of our framework and conduct extensive experiments and simulations on it. Evaluation and analysis results indicate that our framework can not only strengthen system security and data privacy but also reduce communication complexity by \(O(\frac{n\sqrt {m}}{m^2})\) times compared to existing sharding protocols.
Several emerging areas, such as sensor networks, the Internet of Things (IoT), and distributed networks are gaining traction where resource-constrained devices communicate by sharing privacy-preserving information. Due to heavy cryptographic components, standard cryptographic algorithms do not fit these IoT devices. In this article, we propose an efficient zero-knowledge blockchain-based privacy-preserving decentralized healthcare finance system that is suitable for lightweight computer devices. The proposed design mainly focuses on noninteractive zero-knowledge proof, which substantially reduces the cost of communication between two devices. We explain the system framework and its use case for a healthcare financial system at a micro-level. However, it can also be extended easily to more general financial systems. Our system framework is efficient and lightweight, using more efficient zero-knowledge-based proofs; validation of the transactions is done in milliseconds. As an advancement to our work, the proposed healthcare financial system for lightweight computer devices is also auditable without leaking any extra information than required.