Federated learning is a technique that enables multiple parties to collaboratively train a model without sharing raw private data, and it is ideal for smart healthcare. However, it raises new privacy concerns due to the risk of privacy-sensitive medical data leakage. It is not until recently that the privacy-preserving FL (PPFL) has been introduced as a solution to ensure the privacy of training processes. Unfortunately, most existing PPFL schemes are highly dependent on complex cryptographic mechanisms or fail to guarantee the accuracy of training models. Besides, there has been little research on the fairness of the payment procedure in the PPFL with incentive mechanisms. To address the above concerns, we first construct an efficient non-interactive designated decryptor function encryption (NDD-FE) scheme to protect the privacy of training data while maintaining high communication performance. We then propose a blockchain-based PPFL framework with fair payment for medical image detection, namely ESB-FL, by combining the NDD-FE and an elaborately designed blockchain. ESB-FL not only inherits the characteristics of the NDD-FE scheme, but it also ensures the interests of each participant. We finally conduct extensive security analysis and experiments to show that our new framework has enhanced security, good accuracy, and high efficiency.
Roseline Oluwaseun Ogundokun, Sanjay Misra, Rytis MaskeliĹŤnas, Robertas DamaĹĄeviÄius
Federated learning (FL) is a scheme in which several consumers work collectively to unravel machine learning (ML) problems, with a dominant collector synchronizing the procedure. This decision correspondingly enables the training data to be distributed, guaranteeing that the individual deviceâs data are secluded. The paper systematically reviewed the available literature using the Preferred Reporting Items for Systematic Review and Meta-analysis (PRISMA) guiding principle. The study presents a systematic review of appliable ML approaches for FL, reviews the categorization of FL, discusses the FL application areas, presents the relationship between FL and Blockchain Technology (BT), and discusses some existing literature that has used FL and ML approaches. The study also examined applicable machine learning models for federated learning. The inclusion measures were (i) published between 2017 and 2021, (ii) written in English, (iii) published in a peer-reviewed scientific journal, and (iv) Preprint published papers. Unpublished studies, thesis and dissertation studies, (ii) conference papers, (iii) not in English, and (iv) did not use artificial intelligence models and blockchain technology were all removed from the review. In total, 84 eligible papers were finally examined in this study. Finally, in recent years, the amount of research on ML using FL has increased. Accuracy equivalent to standard feature-based techniques has been attained, and ensembles of many algorithms may yield even better results. We discovered that the best results were obtained from the hybrid design of an ML ensemble employing expert features. However, some additional difficulties and issues need to be overcome, such as efficiency, complexity, and smaller datasets. In addition, novel FL applications should be investigated from the standpoint of the datasets and methodologies.
Zhen Qin, Xueqiang Yan, MengChu Zhou, Shuiguang Deng
Federated learning (FL) enables collaborative training of machine learning models without sharing training data. Traditional FL heavily relies on a trusted centralized server. Although decentralized FL eliminates the central dependence, it may worsen the other inherit problems faced by FL such as poisoning attacks and data representation leakage due to insufficient restrictions on the behavior of participants, and heavy communication cost, especially in fully decentralized scenarios, i.e., peer-to-peer (P2P) settings. In this paper, we propose a blockchain-based fully decentralized P2P framework for FL, called BlockDFL. It takes blockchain as the foundation, leveraging the proposed PBFT-based voting mechanism and two-layer scoring mechanism to coordinate FL among peer participants without mutual trust, while effectively defending against poisoning attacks. Gradient compression is introduced to lowering communication cost and prevent data from being reconstructed from transmitted model updates. Extensive experiments conducted on two real-world datasets exhibit that BlockDFL obtains competitive accuracy compared to centralized FL and can defend poisoning attacks while achieving efficiency and scalability. Especially when the proportion of malicious participants is as high as 40%, BlockDFL can still preserve the accuracy of FL, outperforming existing fully decentralized P2P FL frameworks based on blockchain.
Widespread applications of 5G technology have prompted the outsourcing of computation dominated by the Internet of Things (IoT) cloud to improve transmission efficiency, which has created a novel paradigm for improving the speed of common connected objects in IoT. However, although it makes it easier for ubiquitous resource-constrained equipment that outsources computing tasks to achieve high-speed transmission services, security concerns, such as a lack of reliability and collusion attacks, still exist in the outsourcing computation. In this paper, we propose a reliable, anti-collusion outsourcing computation and verification protocol, which uses distributed storage solutions in response to the issue of centralized storage, leverages homomorphic encryption to deal with outsourcing computation and ensures data privacy. Moreover, we embed outsourcing computation results and a novel polynomial factorization algorithm into the smart contract of Ethereum, which not only enables the verification of the outsourcing result without a trusted third party but also resists collusion attacks. The results of the theoretical analysis and experimental performance evaluation demonstrate that the proposed protocol is secure, reliable, and more effective compared with state-of-the-art approaches.
Fatemeh Ghovanlooy Ghajar, Axel Sikora, Dominik Welte
Industrial companies can use blockchain to assist them in resolving their trust and security issues. In this research, we provide a fully distributed blockchain-based architecture for industrial IoT, relying on trust management and reputation to enhance nodesâ trustworthiness. The purpose of this contribution is to introduce our system architecture to show how to secure network access for users with dynamic authorization management. All decisions in the system are made by trustful nodesâ consensus and are fully distributed. The remarkable feature of this system architecture is that the influence of the nodesâ power is lowered depending on their Proof of Work (PoW) and Proof of Stake (PoS), and the nodesâ significance and authority is determined by their behavior in the network. This impact is based on game theory and an incentive mechanism for reputation between nodes. This system design can be used on legacy machines, which means that security and distributed systems can be put in place at a low cost on industrial systems. While there are no numerical results yet, this work, based on the open questions regarding the majority problem and the proposed solutions based on a game-theoretic mechanism and a trust management system, points to what and how industrial IoT and existing blockchain frameworks that are focusing only on the power of PoW and PoS can be secured more effectively.
Abstract The prominent achievement of blockchain technology stimulates exceptional innovation. The major component of blockchain is the consensus mechanism. The standard consensus mechanisms specifically ProofâofâWork (PoW) rely on mining procedures and stakeâbased mechanisms such as ProofâofâStake (PoS) rely on massive stake investment as the sole criteria for selection of leader nodes. However, PoW impose huge computational power requirements and latter may incorporate malicious nodes as leader nodes in anonymous blockchain. These issues might fuel the way for distrust among the participants in blockchain. Henceforth, a novel game theory based reliable PoS mechanism for blockchain has been proposed. Federated learning has been used to compute trust_score for each node. The nodes are trained on locally generated dataset. Further, a game theoretic approach has been proposed that uses a reward and punishment scheme to ensure threshold level of trust_score maintenance by each node. Finally, a crop insurance use case has been developed with the consensus mechanism and blockchain coded in python. The insurance claims are made to operate through smart contract based mobile app system to impart more authenticity. The system is tested and results show an intrusion accomplishment rate reduced by approximate 40% when compared to the standard PoS mechanism and by approximately 33% for algorand, 29% for ouroboros and 20% for tendermint. The mean absolute error also decreases by 30% within specific time. Furthermore, the proposed federated learningâbased system is compared with basic neural networkâbased machine learning model and the results reveal that a significant reduction in average training time amounting to 8.35 second is achieved. Test accuracy has also been analyzed for various learning mechanisms.
G. Ramesh, Avinash Sharma, D. V. Lalitha Parameswari, Ch. Mallikarjuna Rao ¡ 5 authors
Biomedical databases or repositories have scientific information that is evidence based and protecting such documents from tampering or non-repudiation is very significant. The traditional techniques for the same have limitations in the distributed environments. Scientific contributions are to be safeguarded and it is one of the challenging problems. Blockchain is the promising technology that can support distributed ledger of transactions and thus it is found suitable for protecting biomedical repositories. As blockchain is a proven technology associated with crypto-currency known as Bitcoin in finance domain, it has plenty of opportunities in other domains. In this paper, a framework that is based on blockchain technology (BCT) for protection of biomedical databases with integrity and non-repudiation is presented. The framework will have underlying mechanisms to exploit blockchain to have a protection service and smart contracts to be more flexible and dynamic to adapt new requirements from time to time. The framework is domain specific but can pave way for motivation for adapting it to new domains as well.
Blockchain Technology Applications and Security
Privacy-Preserving Technologies in Data
Artificial Intelligence in Healthcare and Education
Privacy and data security have become the new hot topic for regulators in recent years. As a result, Federated Learning (FL) (also called collaborative learning) has emerged as a new training paradigm that allows multiple, geographically distributed nodes to learn a Deep Learning (DL) model together without sharing their data. Blockchain is becoming a new trend as data protection and privacy are concerns in many sectors. Technology is leading the world and transforming into a global village where everything is accessible and transparent. We have presented a blockchain enabled security model using FL that can generate an enhanced DL model without sharing data and improve privacy through higher security and access rights to data. However, existing FL approaches also have unique security vulnerabilities that malicious actors can exploit and compromise the trained model. The FL method is compared to the other known approaches. Users are more likely to choose the latter option, i.e., providing local but private data to the server and using ML apps, performing ML operations on the devices without benefiting from other usersâ data, and preventing direct access to raw data and local training of ML models. FL protects data privacy and reduces data transfer overhead by storing raw data on devices and combining locally computed model updates. We have investigated the feasibility of data and model poisoning attacks under a blockchain-enabled FL system built alongside the Ethereum network and the traditional FL system (without blockchain). This work fills a knowledge gap by proposing a transparent incentive mechanism that can encourage good behavior among participating decentralized nodes and avoid common problems and provides knowledge for the FL security literature by investigating current FL systems.
Eivind Solberg Rydningen, Erika Ă sberg, Letizia Jaccheri, Jingyue Li
The merging of Distributed Ledger Technology (DLT) and the Internet of Things (IoT) has opened new opportunities for innovation in health data management. Issues such as security breaches, privacy violations and fragmented data are just some of the problems that DLT might solve. This research investigates how the IOTA Tangle can provide reliable and secure health data management.
Mr. Anuj Mali, Mr. Bharath Shinde, Mr. Sahil Sharma, Mr. Saurabh Khatal ¡ 5 authors
Block chains are now firmly established as a digital technology that combines cryptographic, data management, networking, and incentive mechanisms to support the verification, execution, and recording of transactions between parties. While block chain technologies were originally intended to support new forms of digital currency for easier and secure payments, they now hold great promise as a new foundation for all forms of transactions. Agribusiness stands to become a key beneficiary of this technology as a platform to execute âsmart contractsâ for transactions, particularly for high-value produce. First it is important to distinguish between private digital currencies and the distributed ledger and block chain technologies that underlie them. The distributed and cross-border nature of digital currencies like Bitcoin means that regulation of the core protocols of these systems by central banks is unlikely to be effective. Monetary authorities are focused more on understanding âon-rampsâ and âoff-rampsâ that constitute the links to the traditional payments system rather than being able to monitor and regulate the currency itself. In contrast to the digital currency feature of block chain, the distributed ledger feature has the potential for widespread use in agribusiness and trade financing, especially where workflows involve many different parties with no trusted central entity.
Mr. Anuj Mali, Mr. Bharath Shinde, Mr. Sahil Sharma, Mr. Saurabh Khatal ¡ 5 authors
Block chains are now firmly established as a digital technology that combines cryptographic, data management, networking, and incentive mechanisms to support the verification, execution, and recording of transactions between parties. While block chain technologies were originally intended to support new forms of digital currency for easier and secure payments, they now hold great promise as a new foundation for all forms of transactions. Agribusiness stands to become a key beneficiary of this technology as a platform to execute âsmart contractsâ for transactions, particularly for high-value produce. First it is important to distinguish between private digital currencies and the distributed ledger and block chain technologies that underlie them. The distributed and cross-border nature of digital currencies like Bit coin means that regulation of the core protocols of these systems by central banks is unlikely to be effective. Monetary authorities are focused more on understanding âon-rampsâ and âoff-rampsâ that constitute the links to the traditional payments system rather than being able to monitor and regulate the currency itself. In contrast to the digital currency feature of block chain, the distributed ledger feature has the potential for widespread use in agribusiness and trade financing, especially where workflows involve many different parties with no trusted central entity.
Medical data sharing is of great significance in promoting smart medicine. However, the heterogeneity of information systems used by various medical institutions makes sharing difficult. In addition, since medical data involves a great deal of sensitive information, sharing it could easily lead to the leakage of personal privacy. Blockchain, gained popularity as a distributed ledger technology, has great potential to connect heterogeneous systems and provides authenticity and integrity guarantees for medical data sharing. Focusing on the issues of medical data sharing and privacy protection, we propose a medical data sharing scheme based on consortium blockchain. To achieve access control, attribute-based access control technique is implemented, where patients preset attribute-specific access policies for their medical records, and record requesters are described by a set of attributes. For patients, we devise a hybrid storage mode to write access policies of medical records on the consortium blockchain network and store encrypted medical records off-chain. Leveraging blockchain and smart contracts, access privilege control and access history tracking can be realized. To enhance the key management, a tree of medical records is constructed for each patient, and by simply keeping the medical record trees, patients can recover their encryption keys at any time. Furthermore, we carry out an extensive analysis to show the high security and efficiency of our proposed scheme. Finally, we build a Quorum consortium blockchain on the Tencent Cloud and deploy smart contracts on the chain to simulate transactions in our scheme. The experiment results indicate the proposed scheme achieves good feasibility.
Tao Wang, Jingyi Wang, Qiliang Yang, Bo Yang ¡ 7 authors
Blockchain-enabled Internet of Things (IoT) provides a secure sharing of data and resources to the various miners of the IoT network, removes centralized control, and can overcome part of the existing challenges in traditional IoT. However, the IoT ecosystem faces some great challenges in terms of security, such as privacy leaking, eavesdropping, and so on, which seriously impede the deployment of the IoT ecosystem. Verifiable searchable encryption (SE) can make data owners (DOs) in the IoT dispel concerns about privacy and make data users (DUs) believe they get correct search results. For the blockchain-enabled IoT, this article proposes an efficient verification SE scheme with aggregation authorization and trusted revocation. With this scheme, DOs are willing to share their data to DUs for reward in a secure, efficient, and trusted way. For the DU, the DO can generate an aggregating key of a subset of encrypted documents, and then the DU has the privilege to search these documents and to verify the search results. By utilizing the trusted execution environment, the DO can revoke the search privilege of the DU. We present the analysis to show our proposed scheme achieves confidentiality, soundness, and fair payment at the same time. With the performance evaluations, we prove our proposal practical for blockchain-enabled IoT in terms of computational and smart contracts overhead.
Simon Tschirner, Shashank Tripathi, Mathias Roeper, Markus M. Becker ¡ 5 authors
Blockchains provide environments where parties can interact transparently and securely peer-to-peer without needing a trusted third party. Parties can trust the integrity and correctness of transactions and the verifiable execution of binary code on the blockchain (smart contracts) inside the system. Including information from outside of the blockchain remains challenging. A challenge is data privacy. In a public system, shared data becomes public and, coming from a single source, often lacks credibility. A private system gives the parties control over their data and sources but trades in positive aspects as transparency. Often, not the data itself is the most critical information but the result of a computation performed on it. An example is research data certification. To keep data private but still prove data provenance, researchers can store a hash value of that data on the blockchain. This hash value is either calculated locally on private data without the chance for validation or is calculated on the blockchain, meaning that data must be published and stored on the blockchain -- a problem of the overall data amount stored on and distributed with the ledger. A system we called moving smart contracts bypasses this problem: Data remain local, but trusted nodes can access them and execute trusted smart contract code stored on the blockchain. This method avoids the system-wide distribution of research data and makes it accessible and verifiable with trusted software.
Jianbin Wu, Sami Ahmed Haider, Manish Bhardwaj, Aditi Sharma ¡ 5 authors
Recently, data integrity for multiagent-based big data environments has been challenging. This paper presents a blockchain-based Merkle DAG structure (M-DAG) for audit data integrity. M-DAG resolves the problem that arises due to the multicopy of a large data volume in a big data environment. It employed BonehâLynnâShachamâs (BSL) signature to verify the integrity of identical multicopy on big data environments. The proposed M-DAG audit mechanism uses a consortium chain algorithm for decentralized traceability and audit to archive reliable data. The evaluation has been carried out for the efficiency of the data integrity audit.
System information (SI) broadcast is an essential element in 5G, which acts as a bridge between userâs equipment (UE) and gNB, providing users with the critical information to access networks. However, as a typical security attack in ratio access network (RAN), the fake base station (FBS) attack precisely exploits SIâs characteristics in terms of unencrypted broadcast to tamper or replay it to lure users to join. Therefore, protecting SI from being exploited by FBS is still an important issue facing the field of wireless network security. Blockchain, as an emerging distributed ledger technology, has shown great potential with its unique security features in many domains. Therefore, in this paper, we leverage blockchain to secure SI and prove its effectiveness in securing information from an information theory perspective. Specifically, we propose a concise theoretical model to measure the effectiveness of blockchain in wireless network security by mapping blockchain security assurance mechanisms into a physical layer security model. Through numerical analysis, we prove the effectiveness of the proposed mechanism under the condition of many network parameter changes.
E-petition has played an important role in health and politics that collects public opinions and requests a superior or an authority to take actions towards a health or political problem. However, this activity exposes the privacy of the signers who participate to express opinions. In this paper, we propose a privacy-preserving fine-grained e-petition system that supports attribute-based identity verification for signers, while protecting their privacy. By considering the target groups of signers in a specific health or political petition, an attribute policy is defined to ensure that only the signers with the attributes that satisfy the attribute policy can sign the petition. The fine-grained petition is better than the traditional e-petitions because it can improve the trustworthiness of the petition results via proactive signer selection. Moreover, the new petition system protects the identities of the signers by using the non-interactive zero-knowledge proof system, such that the signers are anonymous in signing petitions. In addition, the proposed petition system supports the tracing of double-signing, a cheating behavior that an anonymous signer can submit more than one signature in a petition without being detected. Finally, we prove that the proposed petition system achieves the desirable security properties, including anonymity, unforgeability, and traceability, and demonstrate that the system is efficient to be implemented on the mobile devices.
S. P. Vorobyev, Svetlana Shirobokova, Vladimir Evsin
As part of the modern approach to “digitalization”, distributed ledger systems are used more intensively as promising tools with a breakthrough innovative potential. This paper presents a possible implementation of a distributed ledger system using the cloud, fog, edge computing, and IoT technology. The paper describes the aspects that should be considered when building a distributed ledger architecture optimization model (dynamic distribution of network services, explosive volumes of maintenance traffic, difficult-to-predict heterogeneous nature of data traffic from various IoT devices). The relevance of using a fractal model to describe data traffic in a distributed ledger network is shown. The research presents a formalized problem definition of minimizing data traffic and network load, which takes into account the distribution of data processing and storing assets, as well as the implementation of services in the cloud, fog, and edge computing environments to create an optimal multilayer topology of the computer network architecture based on a distributed ledger system. The experimental results for Poisson and fractal traffic models obtained using a genetic optimization algorithm with a variable mutation are presented.
Zero-knowledge proofs (ZKP) are a widely used technology for privacy protection and data ownership that allows parties to verify the accuracy of a piece of information without sharing the data. In this study, we developed and performance tested two graph-based zero-knowledge proof methods, the Hamilton Cycle Based ZKP Algorithm (ZKPHC) and the Graph Isomorphism Based ZKP Algorithm (ZKPGI), using an open source library. As the graph sizes increased, we measured and compared the running times of these methods. We tested the completeness and robustness of the ZKPHC protocol for different modes. As the graph used grows, the ZKPHC method, which uses encryption at every stage, works much slower than ZKPGI.
Medical Cyber-Physical Systems support the mobility of electronic health records data for clinical research to accelerate new scientific discoveries. Artificial Intelligence improves medical informatics, but current centralized data training and insecure data storage management techniques expose private medical data to unauthorized foreign entities. In this paper, a Federated Learning-based Electronic Health Record sharing scheme is proposed for Medical Informatics to preserve patient data privacy. A decentralized Federated Learning-based Convolutional Neural Network model trains data locally in the hospital and stores results in a private InterPlanetary File System. A secondary global model is trained at the research center using the local models. Private IPFS secures all medical data stored locally in the hospital. The novelty of this study resides in securing valuable hospital biomedical data useful for clinical research organizations. Blockchain and smart contracts enable patients to negotiate with external entities for rewards in exchange for their data. Evaluation results demonstrate that the decentralized CNN model performs better in accuracy, sensitivity, and specificity, similar to the traditional centralized model. The performance of the Private IPFS exceeds the Blockchain-based IPFS based on file upload and download time. The scheme is suitable for promoting a secure and privacy-friendly environment for sharing data with clinical research centers for biomedical research.
Privacy-Preserving Technologies in Data
Blockchain Technology Applications and Security
Artificial Intelligence in Healthcare and Education