(IJCST-V10I2P1) :yew Kee Wong
(IJCST-V10I2P1) :yew Kee Wong
(IJCST-V10I2P1) :yew Kee Wong
ABSTRACT
Blockchain constructs a distributed point-to-point system, which is a secure and verifiable mechanism for decentralized
transaction validation and is widely used in financial economy, Internet of Things, large data, cloud computing, and edge
computing. On the other hand, artificial intelligence technology is gradually promoting the intelligent development of various
industries. As two promising technologies today, there is a natural advantage in the convergence between blockchain and
artificial intelligence technologies. Blockchain makes artificial intelligence more autonomous and credible, and artificial
intelligence can prompt blockchain toward intelligence. In this paper, we analyze the combination of blockchain and artificial
intelligence from a more comprehensive and three-dimensional point of view. We first introduce the background of artificial
intelligence and the concept, characteristics, and key technologies of blockchain and subsequently analyze the feasibility of
combining blockchain with artificial intelligence. Next, we summarize the research work on the convergence of blockchain and
artificial intelligence in home and overseas within this category. After that, we list some related application scenarios about the
convergence of both technologies and also point out existing problems and challenges. Finally, we discuss the future work.
Keywords — Blockchain, Artificial Intelligence, Autonomy, Cryptography, Privacy Protection
I. INTRODUCTION
Artificial intelligence and blockchain have their own
As the cutting-edge technologies nowadays, blockchain and advantages, but each one of them also has corresponding
artificial intelligence have attracted increasing attention due to drawbacks. Blockchain has problems regarding energy
the irreplaceable role that they play in technological consumption, scalability, security, privacy, and efficiency,
innovation and industrial transformation [1–3]. The concept of while artificial intelligence faces issues such as interpretability
artificial intelligence technology originated from the and effectiveness. As two different research directions, they
Dartmouth Society in 1956. As an essential branch of can be related to each other and have the advantages of natural
computer science, artificial intelligence technology is integration. These two technologies have common demands
dedicated to the research and development of technical for data analysis, security, and trust, and they can empower
sciences used to simulate, extend, and expand human each other. For instance, artificial intelligence depends on
intelligence. In recent years, thanks to the tremendous three key elements: algorithms, computing power, and data,
breakthroughs made in machine learning (especially deep and the blockchain can break the island of data and realize the
learning) [4] and the exponential growth of data, artificial flow of algorithms, computing power, and data resources,
intelligence has ushered in an explosive period. Due to its based on its inherent characteristics, including
advantages in analysis, prediction, judgment, and decision- decentralization, immutability, and anonymization. In
making, artificial intelligence can fundamentally empower addition, blockchain can guarantee the credibility of the
industries such as security, finance, retail, transportation, and original data as well as the audit credibility and traceability of
education [5–8]. Blockchain technology started relatively late, artificial intelligence. Moreover, blockchain can record the
firstly starting with Bitcoin proposed by Satoshi Nakamoto in decision-making of artificial intelligence, which helps to
2008. The blockchain is essentially a distributed ledger [9, analyze and understand the behavior of artificial intelligence
10]. It can use a decentralized consensus mechanism in an and ultimately promotes the decision-making of artificial
environment where different entities participate, without the intelligence, making it more transparent, explainable, and
intervention of a third trusted party. Blockchain also realizes trustworthy. Artificial intelligence can optimize the
the generation and verification of transactions in an untrusted construction of the blockchain to make it more secure, energy-
distributed system, building trust at a lower cost [11]. It is saving, and efficient.
precisely because of this that more and more researchers have
concentrated on blockchain technology [12, 13]. II. ARTIFICISAL INTELLIGENCE
TECHNOLOGY
Artificial intelligence technology started in 1956 and has
experienced three peaks of development from 1956 to 1970,
1980 to 1990, and 2000 to the present. The proposal for protocols based on open rules and algorithms. Each node in
machine learning in 1959 promoted the peak of the first the system always follows these specifications and protocols
development. The United States and Japan were dedicated to during operation. This ensures that every transaction in a
artificial intelligence research in the 1980s and 1990s which trustless environment can guarantee its correctness and
promoted the peak of the second development. Benefiting authenticity. The nodes can securely exchange, record, and
from the breakthrough of deep learning and reinforcement update data, and operations that do not follow the
learning algorithms, the exponential growth of network data specifications and protocols will not take effect.
and the qualitative leap in computing power, artificial
intelligence has entered the third period of rapid development B.4. Immutability
[19, 20]. Artificial intelligence includes the following key
technologies: computational vision technology, natural After the transaction information of the blockchain passes the
consensus of all nodes and is recorded in the block, there is a
language processing technology, cross-media reasoning
technology, intelligent adaptive learning technology, swarm complete backup locally on each node. At the same time, the
intelligence technology, autonomous drone system correlation between blocks is carried out by the hash
algorithm. If you want to tamper with a piece of data, you
technology, smart chip technology, and brain-computer
interface technology, which can be widely used in various need to modify all subsequent blocks, which is very costly.
industries, such as healthcare, driverless cars [21], education B.5. Traceability
development, games, entertainment, Internet of Things
[22, 23], maritime Internet of Things [24, 25], and Each node in the blockchain saves all the records in the
communication networks [26, 27]. history. Any piece of data can be found by traversing the local
blockchain data, which makes all the data on the blockchain
III. BLOCKCHAIN TECHNOLOGY chain traceable.
A. Concept of Blockchain B.6. Programmability
Blockchain technology is a kind of distributed ledger The nature of the blockchain provides a trusted application
technology that stores data in a chain data structure. It is a environment for the execution of smart contracts, so the
new distributed infrastructure and computing paradigm, which blockchain can provide users with programmable data
employs the distributed node consensus algorithm to verify manipulation capabilities. Users can customize smart contract
the transaction data and further synchronize the entire rules that meet their needs. At the same time, due to its open
network, as well as uses cryptography to ensure data security and automatic execution characteristics, it also guarantees the
and credibility [28]. security of assets and data on the chain.
B. Characters of Blockchain C. Concept of Blockchain
B.1. Multicenter
The rich application scenarios of blockchain are basically
The blockchain adopts distributed decentralized storage, so based on the four core technologies of blockchain, namely,
the distributed recording, storage, and update of data can be consensus mechanism, data structure, cryptography, and
realized without a single central point. Since there is no distributed storage. As the key future research direction of
centralized hardware or management organization, any node blockchain technology, cross-training technology has
can operate on the data on the blockchain according to the gradually become one of the core technologies of blockchain.
established rules.
C.1. Consensus Mechanism
B.2. Transparency
To ensure that nodes are willing to take the initiative to keep
The system data of the blockchain is open and transparent, accounts, the blockchain has formed an important consensus
and any node can have a general ledger of the entire network. mechanism. Common consensus mechanisms are as follows:
Except for the private information of the directly related (1) The proof of work mechanism (PoW) is the original
parties of the data being encrypted through asymmetric consensus mechanism, and all participating nodes compete for
encryption technology, the blockchain data are open to all bookkeeping rights by comparing computing power. Since
nodes, so the entire system information is highly open and everyone participates, but only one node can be selected,
transparent. many resources and time costs will be wasted. (2) For the
proof-of-stake (PoS) mechanism, the longer you hold the
B.3. Autonomy digital currency and the more assets you hold, the more likely
this mechanism is to obtain the right to bookkeeping and
The blockchain system has multiple participants, and they rewards, which saves time but easily causes the Matthew
have formulated automatically negotiated specifications and effect. (3) The delegated proof-of-stake mechanism (DPoS)
selects representative nodes for proxy verification and asset transfer and cross-chain communication between chains.
accounting, which is simpler and more efficient, but it also In the cross-chain process, the two most important things are:
sacrifices some decentralization to a certain extent. The first is to recognize atomicity, that is, cross-chain
transactions either happen or do not happen, so that honest
C.2. Data Structure nodes will not be damaged; the second is to ensure that the
total assets on each chain will not decrease.
The blockchain is similar to an iron chain in form, consisting
of one block after another to form a complete chain. Each IV. FEASIBILITY ANALYSIS OF THE
block includes a block header and a block body. The blocks
are linked back and forth through the hash pointer in the block INTEGRATION OF BLOCKCHAIN AND
header. The hash value contained in each block header is ARTIFICIAL INTELLIGENCE
similar to a digital fingerprint of all the data in the previous The combination of artificial intelligence and blockchain is
block, so there is an interlocking connection between each complementary. Blockchain provides a trustworthy foundation
block. This relationship forms a chain. When any data in the for artificial intelligence, and artificial intelligence provides
block are modified, all subsequent hash values will change. the landing conditions for blockchain.
Such a structure and content constitute the entire blockchain.
A. Blockchain Empowers Artificial Intelligence
C.3. Cryptography
A.1. Transparent and Reliable Data Sources
Blockchain uses killer feature-cryptography. The symmetric
To more securely share data among multiple organizations, it
encryption is equivalent to using the same key to open and
is particularly important to ensure the transparency and
lock the door. Asymmetric encryption is equivalent to using a
reliability of data sources. Smart blockchain technology
pair of different keys to open and lock the door, namely,
ensures the transparency of data on the chain through the
public key and private key. If you use the public-key
synchronization of the full ledger of the nodes and ensures the
encryption, you can use the private key to decrypt; if you use
traceability of data through transaction signatures and time
private-key encryption, you can use the public key to decrypt.
stamps and so on after certificate authentication. A transparent
These two keys are generally stored in the user’s personal
and reliable information-sharing channel has been constructed
wallet. Once the private key is lost, the assets are gone. It is
among multiple participants.
relatively safe in the blockchain in which the public key and
private key are formed through multiple transformations, and A.2. Strong Fairness Guarantee
the characters are relatively long and complex [29].
The traditional blockchain system rewards miners who work
C.4. Distributed Storage hard for the normal operation of the system through tokens
and promotes the good operation of the system by ensuring
The most attractive thing about blockchain is its distributed
fairness. The party who misbehaves in multiple parties will be
storage mechanism. The information record on each block in
punished economically, and the honest party will be
the blockchain is recorded by each node participating in the
compensated accordingly. Smart blockchain technology
bookkeeping competition. To prevent some malicious nodes
ensures that system participants can obtain corresponding
from doing damage, the new data in the blockchain that
rewards as long as they honestly abide by the agreement
adopts the PoW consensus mechanism need to be
through automatically executed preset smart contract codes.
unanimously confirmed and agreed upon by most nodes, and
At the same time, the condition-triggered automatic transfer
at least 51% of the nodes must agree. Therefore, it is difficult
mechanism is used to distribute the rewards to the
to tamper with data.
corresponding participants, which provides a strong fairness
C.5. Cross-Chain Technology guarantee for the intelligent scene of multiparty participation.
As increasingly more data content is shared on the chain, the withdraw funds, resulting in a loss of $50 million. Artificial
privacy of users may be directly or indirectly leaked [32]. intelligence technology provides new development
Traditional blockchain systems use pseudonyms, shuffling, opportunities for the intelligentization of blockchain system
and other methods to protect users’ privacy, but malicious security protection and can provide security and technical
attackers can nevertheless steal users’ private information support for the entire life-cycle of blockchain transactions. As
through data mining and analysis. In the new smart blockchain far as the security of smart contracts is concerned, some work
system, some cryptographic technologies with excellent has been done. Raja et al. [39] have used artificial intelligence
security performance are used to protect users’ data privacy. technology to automatically generate smart contracts, so as to
Li et al. [33] proposed a privacy protection scheme based on reduce the vulnerability of smart contracts as much as
ring signatures using an anonymous signature method based possible. Furthermore, data mining and other technologies are
on an elliptic curve encryption algorithm to protect privacy. used to analyze the vulnerabilities of the smart contract, and
Cai et al. [34] provided a privacy protection scheme based on big data analysis is used to check malicious vulnerabilities to
Pedersen’s commitment for the deletable blockchain system, avoid economic losses caused by hackers. The involvement of
which can hold users accountable when necessary while artificial intelligence in the blockchain can make smart
protecting privacy. The Prada-Delgado team [35] used zero- contracts more intelligent and efficient, allowing them to form
knowledge proof technology to identify the Internet of things a more complete code through continuous learning and
devices in the smart blockchain system, which can protect the practice and reshape the capabilities of blockchain smart
data privacy of lightweight devices efficiently and at low cost. contracts.
Artificial intelligence is usually provided by a single unit of In the industrial sector, a large number of mature blockchain
computing capacity or computing platform. With the rapid systems have been put into practical application, and more
increase in the amount of data and the obvious increase in enterprises are increasing investment in the application of
computational complexity, it is difficult for traditional blockchain. However, due to the limitation of data storage
computing platforms to independently provide the computing mode, the blockchain system generally faces serious problems
capacity required for artificial intelligence, and the hardware of simple query function and low query performance. The
costs and maintenance costs of enterprises are also rising [36]. reason is that the underlying data storage systems of most
Blockchain realizes the decentralization of computing blockchain systems use levelDB, a data storage system
capacity with its distributed nature, which is helpful to realize designed for write-intensive applications. At the cost of data
the operation of artificial intelligence models on global mass reading performance, writing performance has improved.
decentralized nodes and realize decentralized computing. Lin With the increase of data and the expansion of applications in
et al. [37] propose a new wireless edge intelligence framework blockchain systems, it is often necessary to deal with frequent
to achieve stable and robust edge intelligence through energy queries. The underlying storage system has excessive writing
collection methods on a permissioned edge blockchain, and performance but insufficient reading performance, which has
design the optimal edge learning strategy to maximize the become the main bottleneck limiting the query performance.
efficiency of edge intelligence. The data-storing methods of blockchain can likewise be
enhanced with the assistance of AI algorithms. Gawas et al.
B. Artificial Intelligence Empowers Blockchain [40] propose an AI-based novel TTA-CB protocol to establish
a secure and distributed blockchain for data management in
The design and operation of blockchain involves thousands of VECONs and utilize a PSO algorithm to solve the optimal
parameters, as well as the trade-off of security, throughput,
data provider selection problem. Artificial intelligence
decentralization, and other parameters. Artificial intelligence technology has brought new opportunities for the
technology can simplify these decisions and optimize the development of blockchain. Through continuous learning and
blockchain to achieve higher performance and better
practice, it has significantly improved the speed of data query
governance. Moreover, artificial intelligence can also improve
and the efficiency of blockchain applications.
the intelligence of blockchain applications and reduce errors
caused by human influence. V. CONCLUSION
B.1. Security As two most cutting-edge technologies, blockchain and
As we all know, unless the adversary owns the majority of artificial intelligence have the corresponding integration
mining rights, blockchain is almost impossible to hack. opportunities in addition to their own advantages, which can
Unfortunately, the programs and functions of decentralized completely revolutionize the information technology in the
applications built on the blockchain platform are not so future. In this paper, we introduce the background knowledge
secure. For example, in the DAO incident [38], hackers took of artificial intelligence and blockchain in detail, conduct an
advantage of loopholes in smart contracts to repeatedly in-depth analysis of the feasibility of the integration of
blockchain and artificial intelligence, and comprehensively
summarize the research work on the integration of blockchain systems,” IEEE Transactions on Wireless Communications,
and artificial intelligence in the domestic market and overseas. vol. 19, no. 6, pp. 4321–4334, 2020.
Finally, we point out the promising application scenarios and
future work. [11] Z. Zheng, S. Xie, H. N. Dai, X. Cheng, and H. Wang,
“Blockchain challenges and opportunities: a
REFERENCES survey,” International Journal of Web and Grid
Services, vol. 14, no. 4, pp. 352–375, 2018.
[1] A. Barredo Arrieta, N. Díaz-Rodríguez, J. Del Ser et al.,
“Explainable Artificial Intelligence (XAI): concepts, [12] M. B. Mollah, J. Zhao, D. Niyato et al., “Blockchain for
taxonomies, opportunities and challenges toward future smart grid: a comprehensive survey,” IEEE
responsible AI,” Information Fusion, vol. 58, pp. 82–115, Internet of Things Journal, vol. 8, no. 1, pp. 18–43, 2021.
2020.
[13] P. K. Sharma, N. Kumar, and J. H. Park, “Blockchain-
[2] Y. Song, Y. Fu, F. R. Yu et al., “Blockchain-enabled based distributed framework for automotive industry in a
internet of vehicles with cooperative positioning: a smart city,” IEEE Transactions on Industrial Informatics,
deep neural network approach,” IEEE Internet of Things vol. 15, no. 7, pp. 4197–4205, 2018.
Journal, vol. 7, no. 4, pp. 3485– 3498, 2020.
[14] T. Baltrušaitis, C. Ahuja, and L. P. Morency,
[3] R. Gupta, S. Tanwar, S. Tyagi, N. Kumar, M. Obaidat, “Multimodal machine learning: a survey and
and B. Sadoun, “Habits: blockchain-based telesurgery taxonomy,” IEEE Transactions on Pattern Analysis and
framework for healthcare 4.0,” in Proceedings of the Machine Intelligence, vol. 41, no. 2, pp. 423–443, 2018.
2019 International Conference on Computer,
[15] B. K. Mohanta, D. Jena, U. Satapathy, and S. Patnaik,
Information and Telecommunication Systems (CITS), pp.
“Survey on IoT security: challenges and solution using
1–5, IEEE, Beijing China, August 2019.
machine learning, artificial intelligence and
[4] J. Wang, C. Jiang, H. Zhang, Y. Ren, and K-C. Cheng, blockchain technology,” Internet of Things, vol. 11, Article
“Thirty years of machine learning: the road to Pareto-optimal ID 100227, 2020.
wireless networks,” IEEE Communications Surveys &
[16] D. Nguyen, M. Ding, P. N. Pathirana, and A.
Tutorials, vol. 22, pp. 1472–1514, 2020.
Seneviratne, “Blockchain and ai-based solutions to combat
[5] W. Sun, N. Xu, L. Wang, H. Zhang, and Y. Zhang, coronavirus (COVID-19)-like epidemics: a
“Dynamic digital twin and federated learning with incentives survey,” Preprints, 2020.
for air-ground networks,” IEEE Transactions on
[17] R. Gupta, A. Kumari, and S. Tanwar, “Fusion of
Network Science and Engineering, p. 1, 2020.
blockchain and artificial intelligence for secure drone
[6] X. Hou, Z. Ren, J. Wang et al., “Reliable computation networking underlying 5G
offloading for edge computing-enabled software-defined communications,” Transactions on Emerging
IoV,” IEEE Internet of Things Journal, vol. 7, pp. 7097– Telecommunications Technologies, vol. 32, no. 1,
7111, 2020. Article ID e4176, 2021.
[7] J. Wang, C. Jiang, Z. Han, Y. Ren, and L. Hanzo, [18] S. Hu, Y. C. Liang, Z. Xiong, and D. Niyato,
“Internet of vehicles: sensing-aided transportation “Blockchain and artificial intelligence for dynamic resource
information collection and diffusion,” IEEE sharing in 6G and beyond,” IEEE Wireless
Transactions on Vehicular Technology, vol. 67, no. 5, Communications, vol. 99, pp. 1–7, 2021.
pp. 3813–3825, 2018.
[19] Du, F. R. Yu, G. Lu, J. Wang, J. Jiang, and X. Chu,
[8] J. Guo, Y. Zhou, P. Zhang, B. Song, and C. Chen, “MEC-assisted immersive VR video streaming over
“Trust-aware recommendation based on heterogeneous terahertz wireless networks: a deep reinforcement
multi-relational graphs fusion,” Information Fusion, vol. learning approach,” IEEE Internet of Things Journal, vol. 7,
74, pp. 87–95, 2021. no. 10, pp. 9517–9529, 2020.
[9] M. B. Mollah, J. Zhao, D. Niyato et al., “Blockchain for [20] Y. Xiao, Q. Pei, T. Xiao, L. Yao, and H. Liu,
the internet of vehicles towards intelligent transportation “MutualRec: joint friend and item recommendations with
systems: a survey,” IEEE Internet of Things Journal, vol. 8, mutualistic attentional graph neural
pp. 4157–4185, 2020. networks,” Journal of Network and Computer
Applications, vol. 177, Article ID 102954, 2020.
[10] J. Feng, F. R. Yu, Q. Pei, J. Du, and L. Zhu, “Joint
optimization of radio and computational resources [21]Wang, C. Jiang, K. Zhang, T. Q. S. Quek, Y. Ren, and L.
allocation in blockchain-enabled mobile edge computing Hanzo, “Vehicular sensing networks in a smart city:
principles, technologies and applications,” IEEE Wireless approach,” IEEE Internet of Things Journal, vol. 8, no.
Communications, vol. 25, no. 1, pp. 122–132, 2017. 4, pp. 2342–2353, 2020.
[22] Y. Song, F. R. Yu, L. Zhou, X. Yang, and Z. He, [32] W. Zhang, M. Li, R. Tandon, and H. Li, “Online location
“Applications of the internet of things (IoT) in smart trace privacy: an information theoretic approach,” IEEE
logistics: a comprehensive survey,” IEEE Internet of Transactions on Information Forensics and Security,
Things Journal, vol. 99, p. 1, 2020. vol. 14, no. 1, pp. 235–250, 2018.
[23] H. Cao, L. Yang, and H. Zhu, “Novel node-ranking [33] X. Li, Y. Mei, J. Gong, F. Xiang, and Z. Sun, “A
approach and multiple topology attributes-based blockchain privacy protection scheme based on ring
embedding algorithm for single- domain virtual network signature,” IEEE Access, vol. 8, pp. 76765–76772,
embedding,” IEEE Internet of Things Journal, vol. 5, 2020.
no. 1, pp. 108–120, 2017.
[34] X. Cai, Y. Ren, and X. Zhang, “Privacy-protected
[24] T. Yang, Z. Jiang, R. Sun, N. Cheng, and H. Feng, deletable blockchain,” IEEE Access, vol. 8, pp. 6060–
“Maritime search and rescue based on group mobile 6070, 2019.
computing for UAVs and USVs,” IEEE Transactions on
Industrial Informatics, vol. 16, no. 12, pp. 7700–7708, [35] M. Á. Prada-Delgado, I. Baturone, G. Dittmann, J.
2020. Jelitto, and A. Kind, “PUF-derived IoT identities in a
zero-knowledge protocol for blockchain,” Internet of
[25] T. Yang, H. Feng, S. Gao et al., “Two-stage offloading Things, vol. 9, Article ID 100057, 2020.
optimization for energy-latency tradeoff with mobile
edge computing in maritime Internet of Things,” IEEE [36] W. Sun, S. Lei, L. Wang, Z. Liu, and Y. Zhang,
Internet of Things Journal, vol. 7, pp. 5954– 5963, 2019. “Adaptive federated learning and digital twin for
industrial internet of things,” IEEE Transactions on Industrial
[26] P. Guo, W. Hou, L. Guo, Z. Cao, and Z. Ning, “Potential Informatics, vol. 17, no. 8, pp. 5605–5614, 2020.
threats and possible countermeasures for photonic
network-on-chip,” IEEE Communications Magazine, vol. [37] X. Lin, J. Wu, A. K. Bashir, J. Li, W. Yang, and J. Piran,
58, no. 9, pp. 48–53, 2020. “Blockchain- based incentive energy-knowledge trading
in IoT: joint power transfer and AI design,” IEEE
[27] X. Li, M. Zhao, Y. Liu, L. Li, Z. Ding, and A. Internet of Things Journal, vol. 99, p. 1, 2020.
Nallanathan, “Secrecy analysis of ambient backscatter
[38] M. I. Mehar, C. L. Shier, A. Giambattista et al.,
NOMA systems under I/Q imbalance,” 2020,
“Understanding a revolutionary and flawed grand
[28] A. Kosba, A. Miller, E. Shi, Z. Wen, and C. experiment in blockchain: the DAO attack,” Journal
Papamanthu, “Hawk: The blockchain model of cryptography of Cases on Information Technology, vol. 21, no. 1, pp. 19–
and privacy-preserving smart contracts,” in Proceedings 32, 2019.
of the IEEE Symposium on Security & Privacy, IEEE,
San Jose,CA,USA, August 2016. [39] G. Raja, Y. Manaswini, G. D. Vivekanandan et al., “AI-
powered blockchain-a decentralized secure
[29] D. He, M. Ma, S. Zeadally, N. Kumar, and K. Liang, multiparty computation protocol for IoV,”
“Certificateless public key authenticated encryption with in Proceedings of the conference IEEE INFOCOM 2020-
keyword search for industrial internet of things,” IEEE IEEE Conference on Computer Communications
Transactions on Industrial Informatics, vol. 14, no. 8, pp. Workshops (INFOCOM WKSHPS), pp. 865–870, IEEE,
3618–3627, 2017. Toronto, ON, Canada, August 2020.
[30] N. Diallo, W. Shi, L. Xu et al., “eGov-DAO: a better [40] M. Gawas, H. Patil, and S. S. Govekar, “An integrative
government using blockchain based decentralized approach for secure data sharing in vehicular edge
autonomous organization,” in Proceedings of the computing using Blockchain,” Peer-to-Peer Networking and
International Conference on Edemocracy Egovernment, pp. Applications, pp. 1–9, 2021.
166–171, Quito Equador, June 2018.
[31] L. Liu, J. Feng, Q. Pei et al., “Blockchain-enabled secure
data sharing scheme in mobile edge computing: an
asynchronous advantage actor- critic learning