Journal of Organizational and End User Computing

Volume 35 • Issue 1

The Application of Big Data and

Artificial Intelligence Technology
in Enterprise Information Security
Management and Risk Assessment
Qi Wang, School of Management, Hefei University of Technology, China & Faculty of Mathematics and Statistics, Suzhou
University, China
Bangfeng Zong, School of Mechanical and Electronic Engineering, Suzhou University, China
Yong Lin, Faculty of Mathematics and Statistics, Suzhou University, China
Zhuangzhuang Li, Faculty of Mathematics and Statistics, Suzhou University, China*
Xv Luo, Suzhou Bangcai Education Technology Co., Ltd., China

ABSTRACT

With the development of digitalization and Internet technology, enterprise information security is
facing more and more challenges. Many enterprises have begun to adopt big data (BD) and artificial
intelligence (AI) technology for risk assessment (RA) and prediction to effectively manage information
security risks. This article discusses the application of BD and AI technology in enterprise information
security management (ISM) and RA from two aspects. Firstly, the mobile payment signature scheme
based on number theory research unit is used to improve the security of the mobile payment system.
This scheme uses lattice algorithms to achieve fast key generation, signing, and verification and can
resist traditional cryptographic attacks. Secondly, a set of enterprise ISM and RA system is established,
including risk identification, RA, monitoring and early warning, emergency response, and other links.
BD and AI technology is used to analyze internal and external data to provide accurate RA results
to achieve automated RA.

Keywords
Artificial Intelligence Technology, Big Data, Enterprise Information Security Management, Mobile Payment
Signature Scheme, Risk Assessment

INTRODUCTION

Research Background and Significance

With the development of enterprise application information technology, information security faces
more challenges. Traditional security technologies and methods can no longer meet the growing
needs of enterprises, so it is necessary to introduce new technical means for information security

DOI: 10.4018/JOEUC.326934 *Corresponding Author

This article published as an Open Access article distributed under the terms of the Creative Commons Attribution License
(http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and production in any medium,
provided the author of the original work and original publication source are properly credited.

1
Journal of Organizational and End User Computing
Volume 35 • Issue 1

management (ISM) and risk assessment (RA). As an emerging technology field, big data (BD) and
artificial intelligence (AI) technologies have powerful data processing and analysis capabilities,
which can help enterprises achieve accurate and efficient RA and prediction (Dai, 2022; Meng et al.,
2022). Especially in the hot development of new payment methods, such as mobile payment, how
to ensure information security in the payment process has become an urgent problem to be solved.
Based on this, this paper aims to discuss the application of BD and AI technologies in enterprise
ISM and RA, aiming to provide new solutions to help enterprises ensure information security (Lei
et al., 2022; Ye & Chen, 2021).
The application of BD and AI technologies in enterprise ISM and RA is significant (Wang &
Dai, 2022). First, the accuracy and precision of RA can be improved. BD and AI technologies can
conduct in-depth analysis and mining of massive data to help enterprises identify potential risks and
provide accurate RA results. Second, risk monitoring and early warning can be strengthened. BD and
AI technologies can realize the monitoring and analysis of network traffic and abnormal behavior
to detect and respond to potential risks. Third, it can help enterprises develop a scientific security
strategy. Through the analysis and mining of BD and AI technologies, enterprises can understand
their information security status to provide a basis for formulating scientific and effective security
strategies. Finally, it can improve the efficiency and effectiveness of security management. BD and
AI technologies can realize automated RA and prediction, reduce the burden of security management,
and improve management efficiency and effectiveness.
Based on this, this paper analyzes the specific steps of the mobile payment signature scheme based
on the Number Theory Research Unit (NTRU) lattice, compares its superiority with the traditional
mobile payment signature scheme, constructs the enterprise ISM and RA systems, and evaluates the
system dynamically and in real time through the system performance evaluation index system. The
innovation point of the research is to use the mobile payment signature scheme based on the digital
signature scheme to improve the security of the mobile payment system and establish a set of enterprise
ISM and RA systems, including risk identification, RA, monitoring and early warning, emergency
response, and other links. This paper proposes a new solution for applying BD and AI technologies
in enterprise ISM and RA, which has significant theoretical and practical value.

Research Objective
The main objective of this paper is to discuss the application of BD and AI technologies in enterprise
ISM and RA, aiming to provide new solutions for enterprises to help enterprises protect information
security. Specifically, the objectives include:

1. Research and analyze BD and AI technologies’ application status and trends in enterprise ISM
and RA.
2. Explore a mobile payment signature scheme based on the NTRU lattice to improve the security
of mobile payment systems and conduct relevant experimental verification.
3. Establish a set of enterprise ISM and RA systems, including risk identification, RA, monitoring
and early warning, and emergency response, and use BD and AI technologies to analyze internal
and external data of the enterprise to achieve automated RA.
4. Verify the feasibility and effectiveness of the proposed methods and schemes and evaluate their
application effects, advantages, and disadvantages.

Through the above research, the application and applicability of BD and AI technologies in
enterprise ISM and RA can be deeply understood to provide scientific and reasonable ISM and RA
solutions for enterprises and improve enterprise information security.

2
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

LITERATURE REVIEW

Domestic and foreign scholars have achieved good and representative research results for the application
of BD and AI technologies in enterprise ISM and RA. In terms of cyber-attack detection, researchers
proposed the use of BD and machine learning (ML) techniques for network traffic analysis and threat
identification, such as the use of convolutional neural networks (CNNs) for DDoS attack detection
(Chen & Du, 2022; Liu & Chen, 2023). In terms of RA, the researchers proposed some methods for
RA using ML and data mining (DM) techniques, such as using Support Vector Machines (SVMs)
for malicious traffic detection and classification or using clustering algorithms for unlabeled network
attack detection (Feng & Chen, 2022; Zhang et al., 2022). The NTRU lattice-based cryptographic
algorithm also attracted the attention of researchers. It was widely used in mobile payment, internet
finance, and other fields, such as using the NTRU lattice-based digital signature algorithm to achieve
secure mobile payment (Chen & Du, 2022; Feng et al., 2021).
In terms of network intrusion detection, some researchers proposed the use of ML methods,
such as deep learning and decision trees, for network traffic analysis and threat identification, while
others used rule-based or outlier detection methods (Zhou et al., 2022; Li, 2022). In terms of malware
detection, some researchers proposed the use of ML and feature extraction methods for classification,
such as the use of SVMs and random forests for classification of malicious code (Bar, 2022; Diebig et
al., 2022). In terms of RA, some methods using ML and DM techniques for RA were proposed, such
as using naïve Bayes algorithm for network attack detection and clustering algorithm for vulnerability
scanning (Li et al., 2021; Krans et al., 2022).
In cryptography, some researchers focused on lattice-based cryptographic algorithms and
proposed new signature and encryption schemes, such as digital signature schemes based on the
NTRU lattice (Nyman et al., 2021; Du et al., 2021). Foreign researchers extensively researched BD
and AI technologies in enterprise ISM and RA and had many innovative achievements. However,
some issues, such as algorithm security and privacy protection, also needed to be further studied
(Chen et al., 2020; Hui, 2019). For example, in terms of algorithm security, current research mainly
focuses on applying BD and ML technologies, such as CNNs and SVMs. However, with the increasing
importance of data security and privacy protection, researchers need to pay further attention to the
algorithms’ deposit to ensure that new vulnerabilities and risks are not introduced during ISM and
RA. In addition, when using BD and AI technologies for data analysis and processing, attention must
be paid to protecting users’ and enterprises’ personal privacy and business secrets. Current research
also needs to explore further privacy protection methods and technologies, including differential
privacy and secure multiparty computing, to ensure that sensitive information is not leaked during
data sharing and analysis.
To solve this problem, this paper designs a mobile payment signature scheme based on
the NTRU lattice and an enterprise ISM and RA system. It collects a large amount of data and
extracts valuable information from it. This enables accurate identification of potential threats
and vulnerabilities and can help predict future events. For enterprises, security incidents can be
quickly detected and responded to, and their security policies can be adjusted timely to adapt to
the changing security environment.

RESEARCH MODEL

Mobile Payment Signature Scheme Based on the NTRU Lattice

NTRU is a public-key cryptography system proposed in 1996 by three mathematicians, Jeffrey
Hoffstein, Jill Pipher, and Joseph Silverman. Its name is derived from the initials of Number Theory
Research Unit. Compared with traditional public key cryptosystems, such as RSA and ElGamal, NTRU
has higher security and efficiency and is widely used in information security (Batool & Rong, 2018;
Baek et al., 2015). Mobile payments refer to the use of mobile devices for electronic payments. In

3
Journal of Organizational and End User Computing
Volume 35 • Issue 1

information encryption, a signature refers to the value calculated on a piece of text using a private key,
similar to a digital fingerprint (Chen, 2020; Kim, 2015). A signature can be used to verify whether
the text has been tampered with and signed by the user to whom the private key belongs (Syed, 2016;
Sajeev & Balakrishna, 2017).
The NTRU lattice-based mobile payment signature scheme is a security scheme that uses
the NTRU lattice encryption algorithm to implement a mobile payment signature, which uses a
hash function and NTRU lattice encryption algorithm to ensure the security of the signature (Ya-
Jun & Academy, 2014; Meng & Zhang, 2015). It is divided into three parts: registration process,
authentication process, and payment process, and the NTRU encryption and decryption and signature
algorithms in WPKI digital certificates are used to achieve confidentiality and nonrepudiation of
transactions (Zhu et al., 2018).
The specific steps are as follows:

1. Registration process:
a. Step 1: The user downloads the client and obtains the corresponding WPKI digital certificate.
b. Step 2: The user submits a request for registration information, and the server accepts the
request, exchanges digital certificates with it, and negotiates the session key.
c. Step 3: The user fills in the registration information. An Identity (ID) identifier and an
associated hash function are generated. The server uses the successfully negotiated session
key to encrypt the ID and hash function and feedback on the result.
d. Step 4: The user uses the negotiation secret key to decrypt the encrypted information to
obtain the ID and the corresponding hash function, and the hash function calculates the ID
to receive a hash value 1, which is fed back to the server.
e. Step 5: The server accepts the hash value and calculates the ID with the hash function to
get the hash value 2. The hash value 1 is compared with the hash value 2. If the hash value
is the same, the registration is successful.
2. Authentication process:
a. Step 1: The user side sends an authentication application.
b. Step 2: The server accepts the application and queries the database to determine the
legitimacy of the user. If it is legal, it continues to operate; if it is illegal, it prompts an error.
c. Step 3: The server generates random numbers and sends them to the user.
d. Step 4: The user side uses a one-way hash function to calculate the ID and random number
and obtains the returned data 1 to the server.
e. Step 5: The server also uses the hash function to calculate the ID and random number
to obtain the returned data 2. If the returned data 1 and the returned data 2 are equal, the
authentication is complete; if not, the authentication fails with an error.
3. Payment process:
a. Step 1: The client submits a payment request to the server. The client selects random number
A, calculates the random number with the hash function, calculates the user ID and hash
value with the NTRU encryption algorithm and the proposed MNTRUS-MP signature
algorithm, and feeds the result back to the server.
b. Step 2: After receiving the information, the server decrypts the information to verify whether
the requested information meets the requirements. If it is compliant, the payment process
continues; if not, it is interrupted, and a message that the payment failed is sent.
c. Step 3: After the server sends a request to agree to the cost to the user, the user and the
server negotiate the session key.
d. Step 4: After completing the session key negotiation, the client sends payment information
to the server. First, the client uses a hash function to calculate the payment information to
obtain a digest and signs the digest with the MNTRUS-MP signature algorithm. Then, the

4
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

client encrypts the payment information with the session key and transmits the previous
signature to the server along with the encrypted message.
e. Step 5: After the server receives the information, it first decrypts the payment information
using the session key. Then, it uses the client’s public key to perform an unsigned operation
on the signature and obtain a digest. The server uses the hash function to hash the payment
information to get a new digest and compares it with the digest obtained by the previous
unsigning operation. If the two values are equal, the server processes the payment request
and the service is interrupted. Finally, a message of successful or failed payment is sent to
the user.

The framework of the mobile payment circular system is shown in Figure 1.

After the user selects the goods they want to purchase through the mobile terminal, the system
submits a payment request to the payment server after placing an order. The server processes the
user’s payment request, including the payment information of the affiliated bank and the product
information of the associated shopping platform. In the above interaction, the one-way hash function
ensures the high authentication efficiency, and the NTRU public key cryptography algorithm is used
to ensure the confidentiality of the transmitted information. The five-module functions of the mobile
payment prototype system are shown in Figure 2.
This solution has the following advantages compared to the traditional mobile payment signature
scheme. Using the NTRU lattice encryption algorithm can improve the security and reliability of
signatures. Using hash functions for digest generation and verification can ensure the consistency
and integrity of signature information and avoid tampering and forgery.

Enterprise ISM and RA Systems

Enterprise ISM refers to establishing a series of policies, standards, procedures, and control measures
to ensure that its information systems and related data are protected from unauthorized access,
use, leakage, destruction, or tampering. The goal of enterprise ISM is to protect an organization’s

Figure 1. Mobile payment prototype system architecture

5
Journal of Organizational and End User Computing
Volume 35 • Issue 1

Figure 2. Mobile payment prototype system functions

information assets, including confidentiality, integrity, and availability, to prevent information

security incidents from causing damage to the enterprise. Enterprise information security RA refers to
analyzing multiple threats faced by enterprise information systems and assessing the potential impact
of these threats on enterprise information systems to determine appropriate security precautions.
RA typically includes analyzing and assessing system vulnerabilities, threat intelligence, business
impact, and more. Through RA, enterprises can better understand the exposure and risk profile of
their information systems and take targeted measures to protect the security of information systems.
Enterprise ISM and RA systems play a vital role in enterprise ISM. ISM systems help enterprises
establish and implement information security policies and controls to ensure the security of information
systems and protect against potential threats and attacks. RA systems help enterprises understand the
risks and threats their information systems face, assess their potential impact on the business, and
provide a basis for enterprises to formulate effective risk response strategies. The specific system
architecture is displayed in Figure 3.
As shown in Figure 3, the specific workflow is as follows:

Step 1: The client sends the request. Users use their computer browsers to access the address of the
information security RA system. When system log-in, asset entry, and risk analysis are performed,
the customer’s browser submits data request operations and waits for a response.

6
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

Figure 3. Framework diagram of enterprise ISM system

Step 2: The server processes the request, and the server receives the data request sent by the user
from the browser for analysis. If it is a log-in request, determine whether the account password
is correct; if the information is added, determine whether the user input is valid. The server
determines whether the user’s various requests to the system are legal, processes the request,
finds the database data, and generates response data.
Step 3: The server sends a response, and returns the data requested by the user to the browser.
Step 4: Browser parsing. The browser obtains the data, interprets the execution HTML file, and
presents the user data to the interface.

Figure 4 shows the system function structure diagram.

As shown in Figure 4, complete enterprise ISM and RA systems should include the following
aspects. The first is security policies and standards, which clarify enterprise information security
objectives, policies, and regulatory requirements and provide guidance and recommendations. The
second is to assess potential threats in the enterprise information system and take corresponding
security measures to manage the risks. The third is to provide employees with the necessary
information security knowledge and skills to enhance their security awareness and ability. The
fourth is to monitor and manage all activities in the enterprise information system to detect and
deal with any security violations timely. The fifth is to establish an emergency response plan to
take appropriate measures to deal with and recover in the event of a security incident. Finally,
regular security audits and verification activities ensure the company’s information systems and
data are adequately protected.

7
Journal of Organizational and End User Computing
Volume 35 • Issue 1

Figure 4. Enterprise ISM and RA systems organization chart

EXPERIMENTAL DESIGN AND PERFORMANCE EVALUATION

Experimental Equipment
A new mobile payment scheme based on the NTRU lattice was set up to compare with the traditional
one with an elliptical encryption algorithm to realize the mobile payment signature scheme based on
the NTRU lattice. In the built model, the mobile device was the user’s mobile phone, and the server
device was the computer.
Microsoft Visual Studio 2017 and Microsoft SQL Server 2012 were used for system development
to verify the various performance of enterprise ISM and RA systems, and the required equipment
was a computer.

Experimental Environment
The following test environment was set up to implement the mobile payment signature scheme based
on the NTRU lattice.
The system was Android 6.0, the CPU was Intel Z3570, and the memory was 4G. The mobile test
environment was as follows. The server-side test environment was as follows. The system was Windows
7, the CPU was Intel Core i5-4590, and the memory was 8G. To implement enterprise ISM and RA
system applications, the server deployment environment was set to windows2008r2_64_Enterprise
Edition _EX. The detailed configuration was an 8-core CPU, 32G memory, and 1TB of hard disk
storage. The runtime environment required by the system application was NET Framework.

8
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

Indicator Settings
In the research process, the mobile payment signature scheme based on the NTRU lattice and the
traditional elliptic encryption algorithm was designed to verify the algorithm’s performance from
three indicators: digital certificate generation time, digital certificate authentication time, and
transaction payment time. Digital certificate generation time refers to the time it takes to generate a
digital certificate using an algorithm. Digital certificate authentication time is the time required to
authenticate a digital certificate using an algorithm. Transaction payment time refers to the time it
takes to pay for a transaction using an algorithm.
The created enterprise ISM and RA systems should have four properties: scientific, complete,
realistic, and targeted. Based on these four properties, a series of systematic evaluation indicators
were established, with a total of five first-level indicators and ten second-level indicators, as given
in Table 1.
Four first-level indicators, including system scientificity, integrity, realizability, and pertinence,
and eight second-level indicators were set up to make dynamic real-time evaluations of the entire
system and ensure the regular operation of the actual implementation process.

Research Results
For the mobile payment signature scheme based on the NTRU lattice, the performance evaluation was
carried out from three indicators: digital certificate generation time, digital certificate authentication
time, and transaction payment time. The generation time of digital certificates for different algorithms
under different wireless public key infrastructure security levels is presented in Figure 5.
From Figure 5, under the same security level, the generation time of digital certificates based
on the ECC algorithm in traditional schemes was much greater than that of digital certificates based
on NTRU-based mobile signature payment schemes. The higher the level of security, the more
significant the gap. For example, at 256 bits, the digital certificate generation time of the traditional
scheme was 2,384 ms, and the generation time of the digital certificate of the NTRU-based mobile
signature payment scheme was 707 ms, a difference of 1,677 ms.
In the authentication process mentioned here, the authentication time of different algorithms is
demonstrated in Table 2.
As shown in Table 2, the algorithm authentication speed of the mobile signature payment scheme
was much faster than that of the traditional scheme, which shows that the algorithm performance of
the designed NTRU-based mobile signature payment scheme was better than that of the traditional
scheme. The payment time of transaction schemes under different security levels was compared, and
the results are revealed in Figure 6.

Table 1. Enterprise information security and RA systems indicator design table

First-level indicator Second-level indicator

System scientificity score X System plausibility X1
System authority X2
System integrity score Y System compositional integrity Y1
System functional integrity Y2
System realizability score Z System goal achievement Z1
Service object diversity Z2
System pertinence score P Problem tolerance rate P1
System responsiveness P2

9
Journal of Organizational and End User Computing
Volume 35 • Issue 1

Figure 5. Comparison of digital certificate generation times

Table 2. Authentication time for different algorithms

Scheme Algorithm authentication time

Traditional scheme 16
Mobile signature payment scheme 1

From Figure 6, the mobile payment scheme’s transaction payment speed had significant
advantages over the traditional mobile payment scheme. The mobile payment time of the entire
algorithm was controlled within 300 ms. Moreover, the higher the security level, the more the
advantages of NTRU-based mobile signature payment schemes were pronounced. The four first-level
indicators and eight second-level indicators of the enterprise information security and RA systems
were systematically evaluated, and ten experts were found to score the currently designed system
from four directions. The maximum score was ten points, with a minimum score of zero. The details
of the expert participation score and the indicator score are shown in Figure 7.
From Figure 7, ten experts were invited to evaluate the entire information security and RA systems
indicators. More than seven experts participated in evaluating each indicator, and the average score
data were maintained above 8 points, with a maximum of 9.3. It showed that the information security
and RA systems designed here had a high degree of realization and were achievable. This points the
way for enterprises to improve the efficiency of ISM and RA.

DISCUSSION

In summary, the performance of the mobile payment signature scheme based on the NTRU lattice
has obvious advantages compared with the traditional scheme, and the designed information security
and RA systems performance are also better. In addition, it was compared with other studies. Singh

10
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

Figure 6. Comparison of transaction payment times

Figure 7. Evaluation scores of each indicator of information security and RA systems

and Padhye (2020) proposed an ID blind signature scheme based on the NTRU lattice, which
improved the identity-based blind signature scheme based on the NTRU lattice. The results showed
that the scheme had better safety and higher efficiency. Zhu et al. proposed a lattice-based ID

11
Journal of Organizational and End User Computing
Volume 35 • Issue 1

proxy signing cryptography, and the constructed scheme had both signature encryption and proxy
signature characteristics. The proposed scheme had IND-CCA2 security, SUF-CMA security, strong
identifiability and nonrepudiation, and key dependency (Zhu et al., 2021). Compared with the known
ID-based proxy signing ciphers, the proposed scheme required less computational complexity, a
smaller key size, and a smaller signature tuple size. Zhou and Wang (2020) developed a lightweight
anonymous and antiquantum authentication scheme that enabled mobile nodes to roam securely and
seamlessly across multiple service domains. Specifically, they proposed an NTRU-based certification
scheme for provable security and conditional privacy protection to address these security weaknesses
(Zhou & Wang, 2020). Compared with the existing scheme, the proposed scheme improves efficiency
and can resist quantum attacks. In conclusion, more and more studies show that the signature scheme
based on the NTRU lattice performs well.

CONCLUSION

Research Contribution
This paper proposes a mobile payment signature scheme based on the NTRU lattice and designs an
enterprise ISM and RA system, including risk identification, RA, monitoring and early warning,
and emergency response. Through experiments, the following conclusions are obtained. First,
the performance of the mobile payment signature scheme based on the NTRU lattice has obvious
advantages compared with the traditional scheme. It is significantly superior to conventional
solutions in terms of certificate generation, information authentication, and transaction payment
time. For example, at 256 bits, the digital certificate generation time of the traditional scheme is
2,384 ms, and the generation time of the digital certificate of the NTRU-based mobile signature
payment scheme is 707 ms, a difference of 1,677 ms. Besides, the information authentication
time can even be completed within 1 ms, greatly improving the technical level of information
security assurance.
Furthermore, the expert score of the designed information security and RA systems reaches an
average of more than 8 points at a high and comprehensive level. It provides theoretical support for
the efficiency of enterprise ISM and RA. BD and AI technologies have a wide application prospect
in enterprise ISM and RA, which can create a secure and reliable information system for enterprises
and improve the efficiency and accuracy of enterprise RA and decision-making.

Research Limitations and Future Work

The application of BD and AI technologies in enterprise ISM and RA has made progress, but there
are still shortcomings. It mainly evaluates the indicators of enterprise ISM and RA systems based
on expert evaluation and does not consider user feelings comprehensively. Data analysis samples are
not universal. Future research can focus on improving data quality, establishing accurate, complete,
and reliable data sets through user questionnaires, and promoting the accuracy and credibility of BD
analysis.

ACKNOWLEDGMENT

1. Humanities and Social Science Fund of Ministry of Education:Study on the coupling control
of inventory management and transportation distribution of fresh agricultural products
(22YJAZH051).
2. Major Teaching Research Projects of Anhui Provincial Department of Education: The exploration
and practice of constructing high quality School-local integrated development path in the new
era (2022jyxm1613).

12
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

3. Major Project of Philosophy and Social Science of Anhui University Scientific Research: Research
on the improvement strategy of high-quality development of new agricultural business entities
in Anhui Province.
4. Non-financial research project of Suzhou University (2022xhx251).
5. Key research project of Humanities and Social Sciences in Anhui Universities:Research on
the data-driven innovation value chain and high quality development of technology-intensive
industries in Anhui Province (SK2021A0694).

13
Journal of Organizational and End User Computing
Volume 35 • Issue 1

REFERENCES

Baek, J., Vu, Q. H., Liu, J. K., Huang, X., & Xiang, Y. (2015). A secure cloud computing based framework
for big data information management of smart grid. IEEE Transactions on Cloud Computing, 3(2), 233–244.
doi:10.1109/TCC.2014.2359460
Bar, S. (2022). Use of big data analytics and sensor technology in consumer insurance context: Legal and practical
challenges. The Cambridge Law Journal, 81(1), 165–194. doi:10.1017/S0008197322000010
Batool, H., & Rong, D. U. (2018). Which aspects of big data usage is creating information security concern?
[Bai Tu]. Business and Economic Review, 1(4), 7. doi:10.26689/pbes.v1i4.613
Chen, J., Ramanathan, L., & Alazab, M. (2020). Holistic big data integrated artificial intelligent modeling to
improve privacy and security in data management of smart cities. Microprocessors and Microsystems, 81(3),
103722.
Chen, M., & Du, W. (2022a). Dynamic relationship network and international management of enterprise supply
chain by particle swarm optimization algorithm under deep learning. Expert Systems: International Journal of
Knowledge Engineering and Neural Networks. Advance online publication. doi:10.1111/exsy.13081
Chen, M., & Du, W. (2022b). The predicting public sentiment evolution on public emergencies under deep
learning and internet of things. The Journal of Supercomputing. Advance online publication. doi:10.1007/
s11227-022-04900-x
Chen, Q. (2020). Research on the implementation method of database security in management information
system based on big data analysis. E3S Web of Conferences, 185(3), 02033.
Dai, W. (2022). Application of improved convolution neural network in financial forecasting. [JOEUC]. Journal
of Organizational and End User Computing, 34(3), 1–16. doi:10.4018/JOEUC.289222
Diebig, A. M., Pavlista, V., Kuske, J., Angerer, P., & Schwens, C. (2022). Exploring the barriers to the
implementation of psychosocial risk assessment in micro- and small-sized firms. Zeitschrift für Arbeits- und
Organisationspsychologie A&O, 66(4), 170–183.
Du, G., Liu, Z., & Lu, H. (2021). Application of innovative risk early warning mode under big data technology in
internet credit financial risk assessment. Journal of Computational and Applied Mathematics, 386(12), 113260.
doi:10.1016/j.cam.2020.113260
Feng, B., Sun, K., Zhong, Z., & Chen, M. (2021). The internal connection analysis of information sharing and
investment performance in the venture capital network community. International Journal of Environmental
Research and Public Health, 18(22), 11943. doi:10.3390/ijerph182211943 PMID:34831699
Feng, Z., & Chen, M. (2022). Platformance-based cross-border import retail e-commerce service quality
evaluation using an artificial neural network analysis. Journal of Global Information Management, 30(11),
1–17. doi:10.4018/JGIM.306271
Hui, X. (2019). Challenges and countermeasures of management accounting in the era of big data. World
Scientific Research Journal, 5(10), 115–121.
Kim, J. B. (2015). A study on the development of next generation intelligent integrated security management model
using big data technology. International Journal of Security & Its Applications, 9(6), 217–226. doi:10.14257/
ijsia.2015.9.6.21
Krans, N. A., Ammar, A., Nymark, P., Willighagen, E. L., Bakker, M. I., & Quik, J. (2022). Fair assessment tools:
Evaluating use and performance. NanoImpact, 27, 100402. doi:10.1016/j.impact.2022.100402 PMID:35717894
Lei, Z., Gong, G., Wang, T., & Li, W. (2022). Accounting information quality, financing constraints, and
company innovation investment efficiency by big data analysis. [JOEUC]. Journal of Organizational and End
User Computing, 34(3), 1–21. doi:10.4018/JOEUC.292525
Li, J. (2022). Venture financing risk assessment and risk control algorithm for small and medium-sized enterprises
in the era of big data. Journal of Intelligent Systems, 31(1), 611–622. doi:10.1515/jisys-2022-0047

14
 Journal of Organizational and End User Computing
Volume 35 • Issue 1

Li, P., Guan, Z., Han, C., Hu, S., & Guan, Y. (2021). Narrow density window and risk assessment based on big
data. Journal of Physics: Conference Series, 1757(1), 012105. doi:10.1088/1742-6596/1757/1/012105
Liu, Y., & Chen, M. (2023). The knowledge structure and development trend in artificial intelligence based on latent
feature topic model. IEEE Transactions on Engineering Management, 1–12. doi:10.1109/TEM.2022.3232178
Meng, T., Li, Q., Dong, Z., & Zhao, F. (2022). Research on the risk of social stability of enterprise credit
supervision mechanism based on big data. [JOEUC]. Journal of Organizational and End User Computing,
34(3), 1–16. doi:10.4018/JOEUC.289223
Meng, X., & Zhang, X. (2015). Big data privacy management. Journal of Computer Research & Development,
52, 265–281.
Nyman, R., Kapadia, S., & Tuckett, D. (2021). News and narratives in financial systems: Exploiting big
data for systemic risk assessment. Journal of Economic Dynamics & Control, 1(4), 104119. doi:10.1016/j.
jedc.2021.104119
Sajeev, A., & Balakrishna, R. (2017). Big data information management on secure cloud computing framework
using smart grid. Journal of Advanced Research in Dynamical and Control Systems, 2017(4), 188–193.
Singh, S., & Padhye, S. (2020). Identity based blind signature scheme over NTRU lattices. Information Processing
Letters, 155, 105898. doi:10.1016/j.ipl.2019.105898
Syed, H. H. (2016). A secure private cloud computing based framework for big data information management
of smart grid. Social Science Research Network Electronic Journal, 5(6), 82–85.
Wang, J., & Dai, Y. (2022). The agglomeration mechanism of network emerging E-eommerce industry based
on social science. [JOEUC]. Journal of Organizational and End User Computing, 34(3), 1–16. doi:10.4018/
JOEUC.291561
Ya-Jun, L. I., & Academy, G. P. (2014). Research on public security traffic management under the age of big
data. Journal of Guangxi Police Academy, 16(4), 10–15.
Ye, S., & Chen, M. (2021). Leveraging team expertise location awareness in improving team improvisation: A
dynamic knowledge integration perspective. Psychology Research and Behavior Management, 14, 2135–2146.
doi:10.2147/PRBM.S341685 PMID:34984035
Zhang, H., Fan, L., Chen, M., & Qiu, C. (2022). The impact of SIPOC on process reengineering and
sustainability of enterprise procurement management in e-commerce environments using deep learning. Journal
of Organizational and End User Computing, 34(8), 1–17. doi:10.4018/JOEUC.306270
Zhou, S., Zhou, S., Zheng, Z., Lu, J., & Song, T. (2022). Risk assessment for precise intervention of covid-19
epidemic based on available big data and spatio-temporal simulation method: Empirical evidence from different
public places in Guangzhou, China. Applied Geography (Sevenoaks, England), 143, 102702. doi:10.1016/j.
apgeog.2022.102702 PMID:35469327
Zhou, Y., & Wang, L. (2020). A lattice-based authentication scheme for roaming service in ubiquitous networks
with anonymity. Security and Communication Networks, 2020, 1–19. doi:10.1155/2020/2637916
Zhu, H., Wang, Y., Wang, C., & Cheng, X. (2021). An efficient identity-based proxy signcryption using lattice.
Future Generation Computer Systems, 117, 321–327. doi:10.1016/j.future.2020.11.025
Zhu, H., Wu, J., Shi, H., Wang, C., & Li, Y. (2018). Discussion on information security technology of big data
system. Journal of Physics: Conference Series, 1087, 032001. doi:10.1088/1742-6596/1087/3/032001

15