Blockchain and artificial intelligence are two technologies that, when combined, have the ability to help each other realize their full potential. Blockchains can guarantee the accessibility and consistent admittance to integrity safeguarded big data indexes from numerous areas, allowing AI systems to learn more effectively and thoroughly. Similarly, artificial intelligence (AI) can be used to offer new consensus processes, and hence new methods of engaging with Blockchains. When it comes to sensitive data, such as corporate, healthcare, and financial data, various security and privacy problems arise that must be properly evaluated. Interaction with Blockchains is vulnerable to data credibility checks, transactional data leakages, data protection rules compliance, on-chain data privacy, and malicious smart contracts. To solve these issues, new security and privacy-preserving technologies are being developed. AI-based blockchain data processing, either based on AI or used to defend AI-based blockchain data processing, is emerging to simplify the integration of these two cutting-edge technologies.
Blockchain Technology Applications and Security
Privacy-Preserving Technologies in Data
Artificial Intelligence in Healthcare and Education
Aug 1, 2022·2022 IEEE International Conferences on Internet of Things (iThings) and IEEE Green Computing & Communications (GreenCom) and IEEE Cyber, Physical & Social Computing (CPSCom) and IEEE Smart Data (SmartData) and IEEE Congress on Cybermatics (Cybermatics)
Secure comparison is an important problem in the field of secure computing. A classic example is the Millionaires' problem, which is securely compares the wealth of two millionaires without revealing their wealth. However most traditional secure comparison protocol requires autonomous computation among the participants. It is necessary to ensure that the model of the participants is a semi-honest model, otherwise the protocol will not be able to execute correctly. In this paper, we introduce a semi-honest judge to improve the Damgård-Geisler-KrØigaard(DGK) comparison protocol by using techniques such as zero-knowledge proof and homomorphic encryption. The improved protocol is not only applicable to the malicious participant model, but also the introduced judge would not get any information of data. At last, the security analysis shows that the proposed scheme in this paper can guarantee the data fairness of the comparison protocol while ensuring the privacy security of the participants.
Monirah Ali Aleisa, Mona Alshahrani, Natalia Beloff, Martin White
Artificial intelligence (AI) and blockchain technology (BCT) are considered two of the most trending and disruptive technologies. BCT, although commonly associated with cryptocurrencies, has shown a tremendous impact among many other distributed applications domains. BCT characteristics, such as the distribution of data storage among independent nodes and the use of consensus algorithms offer immutability and transparency and remove the need for a central authority making BCT trustworthy. However, decision-makers and stakeholders currently lack the confidence to overcome uncertainty related to AI technology, which affects the acceptance of AI technology in wider application domains, such as the recruitment process. Furthermore, current research literature does not adequately investigate the role of trust as an integral part of an AI-based recruitment application. Therefore, this paper aims to investigate how emerging BCT and AI technologies can improve decision making and stakeholder trust in a job recruitment system that is traditionally focused on just human expert decision-making. In this paper we propose the design of a new solution for trusting AI in recruitment applications through the use of Blockchain Smart Contracts (TAIRA-BSC). TAIRA-BSC integrates Blockchain Smart Contracts (BSC) with the Data Lake (DL), Machine Learning (ML) and AI technologies in our AI Recruitment Model (AIRM) architecture. TAIRA-BSC improves transparency and interoperability in the recruitment process while protecting sensitive job candidate data and ensures data integrity delivery and traceability in the recruiting process through a verifiable decentralized ledger, i.e., the blockchain and associated smart contracts. The paper presents a discussion on the state-of-the-art of integrating AI with BCT focusing on how BCT can be used to bridge trust concerns with AI systems. We also present a conceptual architecture TAIRA-BSC proof of concept that is developed to serve as a foundation for future studies focused on enhancing trust in AI applications through the integration of BCT.
With the development of terminal technology and the expansion of application areas, the value of e-government applications and service requirements continue to increase. To develop and apply e-government, data sharing efficiency is essential. Using the e-government data sharing as a research object, a blockchain-based method is developed for optimizing data transfer. Blockchain technology is used for storing and delivering distributed data. Rather than distributing data nodes randomly, our network scenario model employs a matrix lattice model based on a complete undirected graph. Dual optimization is then applied to solve the problem. In order to find the optimal solution, a mathematical model and an artificial neural network are developed. To verify the performance and packet loss rate of the government data transmission method, a case study is conducted. Data Sharing is optimized to increase the lifetime of static aggregation nodes by at least 30% and lifetime of static aggregation nodes by at least 20%. The network lifetime can be extended by optimizing static aggregation nodes. Furthermore,it effectively improves the robustness.
Rosa Pericàs-Gornals, Macià Mut–Puigserver, M. Magdalena Payeras–Capellà
As a result of the declaration of the COVID-19 pandemic, several proposals of blockchain-based solutions for digital COVID-19 certificates have been presented. Considering that health data have high privacy requirements, a health data management system must fulfil several strict privacy and security requirements. On the one hand, confidentiality of the medical data must be assured, being the data owner (the patient) the actor that maintain control over the privacy of their certificates. On the other hand, the entities involved in the generation and validation of certificates must be supervised by a regulatory authority. This set of requirements are generally not achieved together in previous proposals. Moreover, it is required that a digital COVID-19 certificate management protocol provides an easy verification process and also strongly avoid the risk of forgery. In this paper we present the design and implementation of a protocol to manage digital COVID-19 certificates where individual users decide how to share their private data in a hierarchical system. In order to achieve this, we put together two different technologies: the use of a proxy re-encryption (PRE) service in conjunction with a blockchain-based protocol. Additionally, our protocol introduces an authority to control and regulate the centers that can generate digital COVID-19 certificates and offers two kinds of validation of certificates for registered and non-registered verification entities. Therefore, the paper achieves all the requirements, that is, data sovereignty, high privacy, forgery avoidance, regulation of entities, security and easy verification.
The introduction of electronic personal health records (EHR) enables nationwide information exchange and curation among different health care systems. However, the current EHR systems do not provide transparent means for diagnosis support, medical research or can utilize the omnipresent data produced by the personal medical devices. Besides, the EHR systems are centrally orchestrated, which could potentially lead to a single point of failure. Therefore, in this article, we explore novel approaches for decentralizing machine learning over distributed ledgers to create intelligent EHR systems that can utilize information from personal medical devices for improved knowledge extraction. Consequently, we proposed and evaluated a conceptual EHR to enable anonymous predictive analysis across multiple medical institutions. The evaluation results indicate that the decentralized EHR can be deployed over the computing continuum with reduced machine learning time of up to 60% and consensus latency of below 8 seconds.
Abstract Widely adopted blockchain-based fair data exchange protocol have the following problems in multi-party scenario: 1) in multi-buyer v.s. one seller scenario, the negotiation for data availability verification between the buyer and seller reduces transaction throughput greatly. Besides, malicious buyers can launch DoS attacks to prevent the seller from serving others by requiring lots of data availability proofs. 2) in multi-seller v.s. one buyer scenario where the buyer pays for the merged data of all sellers, current protocols treat this as multiple independent transactions, resulting in excessive on-chain costs. Moreover, current protocols neglect that data ownership establishment on-chain may be tampered since the registration info is in plaintext and submitted through the Internet. This paper proposes multi-party non-interactive atomic fair data exchange protocol based on blockchain to solve the above problems, providing data confidentiality, transaction atomic fairness, data intellectual property right protection, and high efficiency. Specifically, we propose transparent zero knowledge proof-based data verification guaranteeing the data confidentiality and transaction fairness. With the proof computed once and used everywhere, transaction throughput is improved greatly and DoS attacks initiated by malicious buyers is prevented. Moreover, the agent representing multi-seller is introduced to reduce on-chain costs. Furthermore, two-stage on-chain ownership registration is proposed to prevent eavesdroppers from impersonating the owner. Finally, we implement a POC (Proof of Concept) of our protocol as the BADE (Blockchain-based multi-party non-interactive Atomic fair Data Exchange). Experiments show that, our throughput within 12 hours is 50 times that of existing solution\cite{ref10}. And in multi-seller scenario, the on-chain gas costs of our protocol is reduced by 19.9\%-30.5\% in different seller/buyer ratios. The fairness of data exchange is also ensured by extra gas costs of dishonest party.
Tao Hai, Jincheng Zhou, S. Srividhya, Sanjiv Jain · 6 authors
Abstract Blockchain is the latest boon in the world which handles mainly banking and finance. The blockchain is also used in the healthcare management system for effective maintenance of electronic health and medical records. The technology ensures security, privacy, and immutability. Federated Learning is a revolutionary learning technique in deep learning, which supports learning from the distributed environment. This work proposes a framework by integrating the blockchain and Federated Deep Learning in order to provide a tailored recommendation system. The work focuses on two modules of blockchain-based storage for electronic health records, where the blockchain uses a Hyperledger fabric and is capable of continuously monitoring and tracking the updates in the Electronic Health Records in the cloud server. In the second module, LightGBM and N-Gram models are used in the collaborative learning module to recommend a tailored treatment for the patient’s cloud-based database after analyzing the EHR. The work shows good accuracy. Several metrics like precision, recall, and F1 scores are measured showing its effective utilization in the cloud database security.
Social Internet of Vehicles (SIoV) is an emerging technology in the smart city environment, enabling smart vehicles to form social groups and exchange data among themselves. SIoV facilitates many applications aiming to improve driving safety and traffic monitoring by sharing data among vehicles. It ensures a safe and comfortable drive. However, privacy, data confidentiality, and data integrity are the major challenges during multi-hop data transfer that must be addressed for the wide adoption of SIoV. The existing solutions do not provide anonymity and consume more network resources. To address these issues, we propose SIoVChain, a time-lock contract-based privacy-preserving data sharing scheme with incentives for SIoV. It does not only enable data sharing between vehicles anonymously but incentivizes them also. In addition, the proposed framework imposes a penalty anonymously if a malicious vehicle disseminates false information. SIoVChain is shown to be secure against stealing processing fee attack while preserving sender-receiver privacy and path privacy. Universal Composability (UC) framework is used to verify user privacy. The feasibility and efficiency of the scheme are also demonstrated.
In medical scenarios supported by edge clouds, it is difficult for patients to truly gain ownership of their electronic health records (EHRs). However, it is easy for doctors to modify hospital data to deny incorrect treatment records, which makes it difficult to protect the rights of patients. To improve patient control over EHRs, an attribute-based encryption protection scheme named CEC-ABE for EHRs combined with a blockchain is proposed to protect EHRs in edge cloud environments. In this scheme, the agreement process between the patient and the hospital is completed before the ABE stage, and the treatment information, including the treatment time, treatment doctor and additional information, is confidentially transmitted through an encryption algorithm. By storing the uploaded encrypted data in the blockchain in the form of transaction records, the integrity of the data is guaranteed, which facilitates the traceability of EHR generation. Access to EHRs is controlled by the ABE scheme of the outsourced ciphertext policy, and fine-grained attribute revocation can be employed to ensure the security of the ciphertext. The CEC-ABE algorithm, CP-ABE algorithm and other algorithms are experimentally tested, and the computational cost of each stage of the algorithms and the computational delay of each role are compared. CEC-ABE can significantly improve performance in key generation, outsourced decryption and other stages. Compared with the algorithm whose performance is second only to CEC-ABE, it reduces the computational overhead by 1.73% and 5.2%. The results show that the overall comprehensive performance of the CEC-ABE algorithm is better than that of the other algorithms.
The recently emerging federated learning (FL) exploits massive data stored at multiple user nodes to train a global optimal learning model without leaking the privacy of user data. However, it is still inadequate to learn the global model safely at the centralized aggregator, which is an essential part for the traditional FL architecture. Specifically, when using FL in radio access networks to enable edge intelligence, it is difficult for a central server, which belongs to a third party, to guarantee its credibility. Moreover, because the central server may cause a single point of failure, its reliability is also difficult to guarantee. Besides, a malicious participating node of FL may send ill parameters for model aggregation. In this article, we develop a blockchain assisted federated learning (BC-FL) framework, with aim to overcome the single point of failure caused by central server. Meanwhile, we propose to use blockchain to implement auditing of individual involved nodes to ensure the reliability of learning process. To avoid privacy leakage during the audit process to the greatest extent, we design a matching audit mechanism to realize efficient random matching audit process. A cryptocurrency free delegated byzantine fault tolerant (CF-DBFT) consensus mechanism is also designed to realize the low-latency distributed consensus of all nodes in the FL proces. We apply the proposed BC-FL framework to resolve the computing resource allocation problem at the edger servers in MEC network. Simulation results demonstrate the effectiveness and performance superiority of the proposed BC-FL framework. Compared with legacy FL algorithm, the serving time of MEC servers and utilization of computing resource are increased by 35 percent and 48 percent respectively under our proposed BC-FL algorithm.
The fast proliferation of digital twin (DT) establishes a direct connection between the physical entity and its deployed digital representation. As markets shift toward mass customization and new service delivery models, the digital representation has become more adaptive and agile by forming digital twin networks (DTNs). The DTN institutes a real-time single source of truth everywhere. However, there are several issues preventing DTNs from further application, including centralized processing, data falsification, privacy leakage, lack of incentive mechanism, and so on. To make DTN better meet the ever changing demands, we propose a novel block-chain-enabled adaptive asynchronous federated learning (FedTwin) paradigm for privacy-preserving and decentralized DTNs. We design Proof-of-Federalism (PoF), which is a tailor-made consensus algorithm for autonomous DTNs. In each DT's local training phase, generative adversarial network enhanced differential privacy is used to protect the privacy of local model parameters, while a modified Isolation Forest is deployed to filter out the falsified DTs. In the global aggregation phase, an improved Markov decision process is leveraged to select optimal DTs to achieve adaptive asynchronous aggregation while providing a rollback mechanism to redact the falsified global models. With this article, we aim to provide insights to forthcoming researchers and readers in this under-explored domain.
Abstract Artificial intelligence (AI) techniques implemented at a large scale in intelligent transport systems (ITS), have considerably enhanced the vehicles' autonomous behaviour in making independent decisions about cyber threats, attacks, and faults. While, AI techniques are based on data sharing among the vehicles, it is important to note that sensitive data cannot be shared. Thus, federated learning (FL) has been implemented to protect privacy in vehicles. On the other hand, the integrity of data and the safety of aggregation are ensured by using blockchain technology. This paper applied classification approaches to VANET and ITS cyber‐threats detection at the vehicle. Subsequently, by using blockchain and by applying an aggregation strategy to different models, models from the previous step were uploaded in a smart contract. Lastly, we returned the updated models to the vehicles. Furthermore, we conducted an experimental study to measure the effectiveness of the proposed prototype. In this paper, the VeReMi data set was distributed in a balanced manner into five parts in the experimental study. Thus, classification techniques were executed by each vehicle separately, and models were generated. Upon the aggregation of the models in blockchain, they were returned to the vehicles. Lastly, the vehicles updated their decision functions and accessed the precision and accuracy of cyber‐threat detection. The results indicated that the precision and accuracy decreased by 7.1% on average with comparable F 1‐score and recall. Our solution ensures the privacy preservation of vehicles whereas blockchain guarantees the safety of aggregation technique and low gas consumption.
Kota Chin, Keita Emura, Kazumasa Omote, Shingo Sato
In an open-bid auction, a bidder can know the budgets of other bidders. Thus, a sealed-bid auction that hides bidding prices is desirable. However, in previous sealed-bid auction protocols, it has been difficult to provide a ``fund binding'' property, which would guarantee that a bidder has funds more than or equal to the bidding price and that the funds are forcibly withdrawn when the bidder wins. Thus, such protocols are vulnerable to false bidding. As a solution, many protocols employ a simple deposit method in which each bidder sends a deposit to a smart contract, which is greater than or equal to the bidding price, before the bidding phase. However, this deposit reveals the maximum bidding price, and it is preferable to hide this information. In this paper, we propose a sealed-bid auction protocol that provides a fund binding property. Our protocol not only hides the bidding price and a maximum bidding price, but also provides fund binding, simultaneously. For hiding the maximum bidding price, we pay attention to the fact that usual Ethereum transactions and transactions for sending funds to a one-time address have the same transaction structure, and it seems that they are indistinguishable. We discuss how much bidding transactions are hidden. We also employ DECO (Zhang et al,. CCS 2020) that proves the validity of the data to a verifier in which the data are taken from a source without showing the data itself. Finally, we give our implementation which shows transaction fees required and compare it to a sealed-bid auction protocol employing the simple deposit method.
While users enjoy the convenience of data outsourcing in the cloud, they also face the risks of data modification and private information leakage. Searchable encryption technology can perform keyword searches over encrypted data while protecting their privacy and guaranteeing the integrity of the data by verifying the search results. However, some associated problems are still encountered, such as the low efficiency of verification and uncontrollable query results. Accordingly, this paper proposes a Privacy-Preserving Searchable Encryption (PPSE) scheme based on public and private blockchains. First, we store an encrypted index in a private blockchain while outsourcing corresponding encrypted documents to a public blockchain. The encrypted documents are located through the encrypted index. This method can reduce the storage overhead on the blockchains, and improve the efficiency of transaction execution and the security of stored data. Moreover, we adopt a smart contract to introduce a secondary verification access control mechanism and restrict data users' access to the private blockchain through authorization for the purpose of guaranteeing data privacy and the correctness of access control verification. Finally, the security analysis and experimental results indicate that compared with existing schemes, the proposed scheme can not only improve the security of encrypted data but also guarantee the efficiency of the query.
Single Secret Leader Election protocols (SSLE, for short) allow a group of users to select a random leader so that the latter remains secret until she decides to reveal herself. Thanks to this feature, SSLE can be used to build an election mechanism for proof-of-stake based blockchains. In particular, a recent work by Azouvi and Cappelletti (ACM AFT 2021) shows that in comparison to probabilistic leader election methods, SSLE-based proof-of-stake blockchains have significant security gains, both with respect to grinding attacks and with respect to the private attack. Yet, as of today, very few concrete constructions of SSLE are known. In particular, all existing protocols are only secure in a model where the adversary is supposed to corrupt participants before the protocol starts -- an assumption that clashes with the highly dynamic nature of decentralized blockchain protocols. In this paper we make progress in the study of SSLE by proposing new efficient constructions that achieve stronger security guarantees than previous work. In particular, we propose the first SSLE protocol that achieves adaptive security. Our scheme is proven secure in the universal composability model and achieves efficiency comparable to previous, less secure, realizations in the state of the art.
Di Wu, Nai Wang, Jiale Zhang, Yuan Zhang · 6 authors
With the expansion of the Internet of Things (IoT) development and application, federated learning has gained higher popularity in industrial researching fields. However, the security issues in federated learning have become hot-spots in the research area, such as privacy-preserving and poisoning attacks. This paper proposes a robust blockchained multi-layer decentralized federated learning (RBML-DFL) framework to ensure the federated learning's robustness. Firstly, by adopting the three-layered framework, the blockchain connects the federated learning components to secure the privacy and data safety of federated learning. Secondly, the proposed framework provides resilience on poisoning attacks to the central model compared to typical federated learning frameworks. Lastly, the decentralized structure associated with the blockchain tracing back mechanism can prevent the central server failure or mal-function compared to centralized federated learning. We evaluate and compare the proposed framework with other state-of-the-art federated learning frameworks on the accuracy, latency, and system robustness under poisoning attacks. The results show that the proposed RBML-DFL framework outperforms state-of-the-art baseline frameworks on all three metrics: accuracy, latency, and the robustness of the federated learning.
Salabat Khan, Fei Luo, Zijian Zhang, Mussadiq Abdul Rahim · 7 authors
Vehicular social networking is expected to become a reality soon, where secure and privacy-preserving identity management is a prerequisite. Various organizations and studies have recommended using Vehicular Public-key Infrastructure (VPKI) to securely and privately manage vehicles' identities. However, the existing VPKI schemes still do not deal with identity management in vehicular social networking. In this work, we propose a Privacy-Preserving Identity Management (PPTIM) scheme for vehicular social networking to securely and privately manage vehicles' social identities. PPTIM builds on the transparency log (distributed ledger) proposals for web PKI, but it addresses challenges specific to vehicular social networking. All pseudo-social identities, pseudonym certificates issued against pseudo-social identities, revocation process, and revocation status validation are conducted on a transparency log. With an efficient data structure named the Accumulation Tree (AT), we extend the conventional transparency log to offer trustworthy pseudonym certificate validation without relying on the Certificate Revocation Lists (CRLs). In addition, PPTIM strengthens the security of vehicular social networking by protecting vehicles to a greater extent from being duped by malicious pseudonym certificates through logging and constant monitoring. Finally, performance and security analysis show the cost-effectiveness and security of PPTIM.
Multi-organization data sharing is becoming increasingly prevalent due to the interconnectivity of systems and the need for collaboration across organizations (e.g., exchange of data in a supply chain involving multiple upstream and downstream vendors). There are, however, data security concerns due to lack of trust between organizations that may be located in jurisdictions with varying security and privacy legislation and culture (also referred to as a zero trust environment). Hence, in such a zero trust setting, one should introduce strengthened, yet efficient, access control mechanisms to facilitate cross-organizational data access and exchange requests. Contemporary access control schemes generally focus on protecting a single objective rather than multiple parties, due to higher security costs. In this article, we propose a blockchain-based access control scheme, designed to facilitate lightweight data sharing among different organizations. Specifically, our approach utilizes the consortium blockchain to establish a trustworthy environment, in which a Role-Based Access Control (RBAC) model is then deployed using our proposed multi-signature protocol and smart contract methods. Evaluation of our proposed approach is performed on the HyperLedger Fabric consortium blockchain platform using both Caliper and BFT-SMaRT benchmarks, and the findings demonstrate the utility of our approach.
Yanru Chen, Yuanyuan Zhang, Shengwei Wang, Fan Wang · 8 authors
With the development of big data, data sharing has become a hot topic. According to the previous research on data sharing, there is a problem with regard to how to design an effective incentive mechanism to make users willing to share data. First, we integrate the incentives based on reputation and payment and introduce “credibility coins” as a cryptocurrency for data-sharing transactions, to encourage users to participate honestly in the data-sharing process based on federated learning. Second, we propose a dynamic incentive model based on the evolutionary game theory to model the game process of users in data sharing and analyze the stability of their strategies. Finally, based on the results of this analysis, we use the blockchain-based smart contract technology to dynamically adjust the participation benefits of users under different conditions in order to promote users to join consortium blockchains more often and steadily to participate in model training for federated learning and obtain better model accuracy. Our work is the first to apply the evolutionary game theory to the study of incentives in federated learning, and plays a leading role in the study of incentives in federated learning. Experimental simulation validation shows that our DIM-DS model can adequately motivate users to participate in the collaborative task of data sharing and maintain stability. The model can maximize the effectiveness of the federated learning model.
Tianshuai Zhang, Leyou Zhang, Qing Wu, Yi Mu · 5 authors
The application of blockchain to data sharing in an untrusted environment has received widespread industry attention in recent years. However, the tamper-proof property of blockchain brings protection for sharing data and also leads to a new limitation for the deletion of malicious data. Nowadays, many methods based on redactable blockchain with a chameleon hash is proposed to attempt to solve the above problem, but loss of effective access control to the modifiers can easily lead to breaking the positive characteristics of the blockchain. To address the aforementioned problem, a hierarchical access control redactable blockchain model for data sharing through attribute-based encryption and a chameleon hash is introduced. Under this model, the data owner can specify who can modify their data by setting an access policy and authenticating the modifier with a digital signature. The data owner’s full control over rights is guaranteed, while the modifier’s behavior is regulated. In addition, the hierarchical access control decentralized technique solves the overpowerful problem of center authority and single-point-of-failure problems in the existing works. The security analysis indicates that the proposed scheme achieves indistinguishable chosen plaintext attack security as well as collision resistance security. Performance analysis shows that the proposed scheme is more complete and has better efficiency compared with other schemes.
From tracking pandemics to applications, such as Google Maps, Uber, environmental monitoring, journalism, healthcare, crisis/disaster response, air quality control, noise and traffic monitoring, urban planning, etc., mobile crowdsourcing (MCS) systems are interweaved with the society and daily lives. This survey outlines major security and privacy challenges in MCS systems along with solutions and approaches. Comprehensive countermeasures, leveraging the capabilities of blockchains, smart contracts, machine learning, games, incentives, spatiotemporal cloaking, etc., are presented to preserve privacy and security of mobile workers, task requestors, and other aspects of crowdsourcing systems. Security recommendations for use cases, such as Industrial IoT, Internet of Vehicles, wireless crowdsensed systems, social crowdsourcing, edge computing, personalized and privacy-preserving recommendation, and mobile worker recruitment are further elaborated.