Materials Today: Proceedings xxx (xxxx) xxx

Contents lists available at ScienceDirect

Materials Today: Proceedings

journal homepage: www.elsevier.com/locate/matpr

Effectiveness of artificial intelligence techniques against cyber security

risks apply of IT industry
Bilal Alhayani a,⇑, Husam Jasim Mohammed b,⇑, Ibrahim Zeghaiton Chaloob c, Jehan Saleh Ahmed c
a
Department of Electronics and Communication, Yildiz Technical University, Istanbul, Turkey
b
Department of Business Administration, Collage of Administration Sciences and Financial, Imam Ja’afar Al-Sadiq University, Baghdad, Iraq
c
College of Applied Science, Fallujah University, Anbar, Iraq

a r t i c l e i n f o a b s t r a c t

Article history: The aim of the researcher was to determine the effectiveness of artificial intelligence techniques against
Received 7 February 2021 cyber security risks particularly in case of Iraq, Researcher has opted for quantitative method of research
Received in revised form 7 February 2021 design along with primary data. The researcher collected the data from employees working in this IT
Accepted 16 February 2021
industry. The sample size for this study was 468 and confirmatory factor analysis, discriminant validity,
Available online xxxx
basic analysis of model and lastly, hypothesis assessment was carried out. The P-values of all variables
were obtained as significant apart from expert system which had no significant relation with artificial
Keywords:
intelligence and cyber security. Geographical area, sample size, less variables and accessibility was the
Artificial intelligence
Expert system
main issue.
Neural agents Ó 2021 Elsevier Ltd. All rights reserved.
Cyber-security Selection and peer-review under responsibility of the scientific committee of the Emerging Trends in
Intelligence agents Materials Science, Technology and Engineering.

1. Introduction services, spyware and malware infections that can result in

affecting everyone in the country. Cyber-attacks also result in
In the contemporary environment, the protection against causing major psychological effects among the individuals
cyber-attacks has become a vital and urgent issue which involves resulting in frustration, stress and anxiety.
protecting the computer system from possible threats [1]. White Taddeo in [5] pointed out that the artificial intelligence (AI) is
in [2] has depicted that the term cyber-attack defined by the U.S an effective activity for reducing the impact of cyber-attacks. Bha-
Federal Bureau Investigations is a politically involved attack tele et al. in [6] have defined AI as the machine intelligence that
against computer systems, information, program and data that performs tasks that are associated with the intelligence being.
results in causing violence against non-combatant targets by The knowledge of human experts is embedded for the decision
sub-national groups. Advancement in technology is also leading making such as for conducting medical diagnosis and gaining
to higher cyber threats which requires in developing new preven- insights from knowledge in making a decision. In respect to cyber
tive measures. Huang et al. in [3] has indicated that cyber-attacks security, Taddeo in [5] has demonstrated that AI causes both bad
are increasing in the industrial area that leads towards physical and good effects in which the bad effects of AI is that it has a risk
damages to the facilities that leads to potential loss of million dol- of facilitating the escalation process of the attacks for causing fas-
lar worth. The rationale behind the increase of cyber-attacks ter and more impactful attacks. Moving towards good effect, AI
among companies is mainly due to the increasing dependence leads to significantly improving the cyber security along with
on digital technology which causes the financial and personal enhancing defensive measures and fostering security in cyber-
information to be stored. Thus, it is considered as the most impor- space. In addition, Conti et al. in [7] that AI provides the security
tant challenges in the current scenario as it not only leads to professionals for identifying cyber threat indicators. AI has led to
financial loss but also causes leakage to sensitive information. increasing usage of machine learning for conducting malware
According to [4], the cyber-attacks range from hacking, denial of analysis along with network anomaly detection.
With respect to the literature, the following study is mainly
⇑ Corresponding authors. conducted to analyze the effectiveness of artificial intelligence
E-mail addresses: [email protected] (B. Alhayani), [email protected]. techniques for enhancing against cyber security risks particularly
iq (H. Jasim Mohammed).

https://doi.org/10.1016/j.matpr.2021.02.531
2214-7853/Ó 2021 Elsevier Ltd. All rights reserved.
Selection and peer-review under responsibility of the scientific committee of the Emerging Trends in Materials Science, Technology and Engineering.

Please cite this article as: B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al., Effectiveness of artificial intelligence techniques against cyber secu-
rity risks apply of IT industry, Materials Today: Proceedings, https://doi.org/10.1016/j.matpr.2021.02.531
B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al. Materials Today: Proceedings xxx (xxxx) xxx

in Iraq. For instance, the study conducted by [5] has depicted that by client or software. Expert systems are provided in different
AI has both good and bad effect on cyber-security as it can either forms which ranges from small system to hybrid system that is uti-
escalate the process of attacks of causing faster and painful attacks lized for diagnostic purposes. In addition, the system is utilized for
or can result in enhancing the cyber security. Hence, the primarily providing security in the cyber defence [28–31]. Similarly, the
objective of the research is to determine the role of AI in Iraq in study conducted by [32] has depicted that expert system utilizes
countering against the cyber-attacks that leads to enhancing the input data for identifying vulnerability along with the threat
cyber-security. The significance of the study is that it provides level related to the transaction on E-commerce websites. Hence,
the importance of AI technologies among the IT professionals for in this manner, the following hypothesis has been developed for
taking preventive measure against cyber-attacks. expert system.
H2: Expert system has a significant and positive role on the
artificial intelligence
2. Literature review H3: Artificial intelligence has a significant mediating effect between
the expert system and cyber-security
In Iraq, the admittance of internet in 2016 has increased to Another effective technology and advanced branch for the AI is
74.9% from 47% in 2011 where it illuminates that 24 million indi- the neural nets which is also known as the deep learning. It was
viduals are utilizing the internet for social media, internet-based mainly inspired by the functions of the human brain that was asso-
games and other. Iraq Telecom is mainly responsible for the distri- ciated with several neurons that can learn any type of data. When
bution of the internet to the customers. However, with the incline applied with the cyber-security, the system can support in identi-
of internet usage has also led to the increase of computer crimes. fying whether there is a file malicious or legitimate without the
There are particularly three major cases that have occurred in Iraq interference of human. Neural nets yields a strong result in deter-
regarding cybercrime. The first major case is reflected to the State mining the malicious threats in comparison with the classical
oil company where it was hit by virus in 2012 that resulted in caus- machine learning system [33–36]. In addition, [37] has similarly
ing demolition to information and drives to computer which was depicted that neural network allows in easily monitoring the secu-
aimed to stopping the oil production. The second major case is rity of the computer while also taking remedial action. Hence, in
related with Baghdad University which was hacked where the last this perspective, the following hypotheses are designed in respect
major case is reflected to government administration that led to to neural nets:
the disruptions on operations of government [8–14]. In addition, H4: Neural nets has a significant role on the artificial intelligence
study conducted by [15] has depicted that cyber-crimes are for countering against cyber-attacks
increasing around the globe where it is critical for the countries H5: Artificial intelligence has a significant mediating effect between
to have strong cyber-security. Iraq has been taking initiative for the Neural Nets and cyber-security
enhancing the cyber-security by developing laws and regulation As per the study conducted by [33] intelligent agent is an inde-
along with focusing on enhancing cyber-security. pendent entity of the AI where it mainly recognizes the movement
The main idea of AI in Iraq was to enhance the cognitive system through sensors while following the environment actual indication
by developing similar or better intelligence than humans. AI tech- i.e. an agent and directs its overlay activity towards the achieve-
nology has started to infiltrate various industries which comprises ment of goals. Intelligent agent is mainly created for countering
of healthcare, robotics, retail and insurance industry. However, Iraq against the distributed denial of services (DDoS) attacks. The tools
has not yet fully embraced the AI revolutions. It is identified that also have several advantages as it provides with proactive mea-
the country is making significant investment on the artificial intel- sures, mobility and agent communication language. In respect to
ligence by focusing on communication network, accessibility to study of [28], intelligent agents are self-sufficient computer system
mentors, funding, infrastructure development and manufacturers that shares information with each other while fighting cyber
[16–20]. Similarly, study conducted by [21] has indicated that assaults. Moreover, the study also recognizes that the intelligent
the emergence of AI particularly in the higher education of Saudi agent is mainly designed for countering against the DDoS through
Arabi has contributed towards promoting educational quality and the support of cyber agent’s communication and movement. In this
learning outcome. The incorporation of AI has also contributed manner, the following hypotheses are designed for the study that
towards the information technology (IT) in respect to critical think- concentrates on intelligence agent:
ing, communication, problem solving, technological literacy and H6: Intelligence agent has a significant role on the artificial intelli-
creativity. gence for countering against cyber-attacks
In the past few years, many of the researchers have started H7: Artificial intelligence has a significant mediating effect between
exploring the approaches of AI for enhancing the cyber-security. the Intelligence Agents and cyber-security
The term cyber-security is referred to the processes, system and
human behaviour that supporting in safeguarding the electronic
resources. AI has been identified as a versatile technique for deter- 2.1. Conceptual framework
mining false information along with evaluating large amount of
data [22–25]. Similarly, the study conducted by [26] has depicted For the following comprehensive study, the researcher has
that the AI is getting strong recognition towards assisting the users opted for quantitative method of research design along with pri-
for fighting crime and resolving problems in cyber space. AI mainly mary data. The aim of the researcher was to determine the effec-
supports in identifying the viruses, designing solutions and deploy- tiveness of artificial intelligence techniques against cyber security
ing solutions that support in countering against the cyber-crime. risks particularly in case of Iraq. The researcher collected the data
Szychter et al. in [27] has also that many organizations are incor- from employees working in this IT industry of Iraq who possess
porating AI as it can enhance the security of internet of things thorough knowledge about advanced methods such as AI technol-
(IoT) by predicting or detecting malicious activities. In the basis ogy and cyber security issues. The sample size for this study was
of the literature, the following hypothesis has been developed. 468 because with increased sample size, the study becomes more
H1: Artificial intelligence has a significant and positive effect on accurate, reliable and authentic. Other researchers who wish to
cyber-security which reduces the impact of cyber-attack conduct study in similar domain can use this research article as a
The most common tool that is used for the AI is the expert base paper. However, a smaller sample size is always a limitation
system which utilized for identifying inquiries that are presented and does not guarantees the authenticity of the results [38] (Fig. 1).
2
B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al. Materials Today: Proceedings xxx (xxxx) xxx

Fig 1. Conceptual Framework.

A survey questionnaire was used based on Likert scale for used in the study, the appropriate value of 0.6 was set. The table
reaching out to the desired respondents and was distributed below provides overview of the values obtained through factor
among them by self-administering in case of any queries. The loadings, Cronbach Alpha, Composite reliability and AVE (Average
respondents filled the questionnaire as per their opinion and expe- Variance Extracted).
riences and were asked to share to return back. Based on the The Table 1 above shows that all values of factor loadings are
respondent’s own convenience, the questionnaire was returned. above 0.7 which indicates that factors influence the variables
The data was then analysed through the use of Smart PLS. The data strongly. The next important values shown above are Cronbach
analysis techniques adopted were confirmatory factor analysis, Alpha, Composite reliability and AVE. These metrics show the fit-
discriminant validity, basic analysis of model and lastly, hypothesis ness of the model and whether they can be used further for testing
assessment. The data was first tested for determining whether the or not. Cronbach Alpha shows the reliability of the constructs and
variables constructs are related to each other or not. Since the aim desired or optimum value should be above 0.7. The Table 1 clearly
of the researcher was to examine the relationship as well as the indicates that all values are above 0.7 which means that they are
mediation between the variables or not therefore, SEM technique reliable and can be used further.
was used and through multiple regression models, the relationship Composite reliability is another measure for assessing the reli-
between variables was identified. Based on the results obtained, ability of the data and it indicates the internal consistency of the
the hypothesis formed were declared as ‘‘accepted” or ‘‘rejected”. constructs similar to like Cronbach Alpha. The minimum values
of composite reliability should exceed 0.7 in order to ensure high
internal consistency in constructs. On the other hand, AVE (Aver-
3. Result age Variance Extracted) is used to examine the variance that is
explained through the predictors of residual variance. The accepted
3.1. Confirmatory factor analysis benchmark value for it is 0.5 which means that for the variables to
be deemed as significant, their values should exceed 0.5. As shown
In order to find out the overall fitness of the model, confirma- by Table 1 above that AVE values exceed 0.5 and composite relia-
tory factor analysis was used. To determine the fitness of variables bility values also exceed 0.7 indicating that there is internal consis-

Table 1
Confirmatory Factor Analysis.

Factor Loadings Cronbach Alpha Composite Reliability AVE

AI1 0.835 0.896 0.928 0.762
AI2 0.870
AI3 0.886
AI4 0.900
CSY1 0.656 0.790 0.851 0.540
CSY2 0.637
CSY3 0.611
CSY4 0.868
CSY5 0.859
ES1 0.881 0.861 0.915 0.782
ES2 0.907
ES3 0.865
IA1 0.883 0.874 0.923 0.799
IA2 0.921
IA3 0.877
NN1 0.799 0.817 0.891 0.733
NN2 0.894
NN3 0.871

3
B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al. Materials Today: Proceedings xxx (xxxx) xxx

tency in data as well as shows that variables are suitable for further Table 3
testing of hypothesis and model assessment. Model.

R Square R Square Adjusted

3.2. Discriminant validity Artificial Intelligence 0.238 0.233
Cyber Security 0.636 0.635
The second phase of testing in this research article includes of
discriminant validity. The purpose of using discriminant validity
is to find out the accuracy of the variables used in the study. It also reliability and internal consistency, now the researcher examines
explains the overall magnitude of whether a variable is related whether the hypothesis was achieved or not.
with other variables or not. The results below show whether the Based on the results shown in the Table 5 above, it is evident
constructs are related to each other or not. that apart from expert system, all other hypothesis were accepted.
The Table 2 above show that discriminant validity is assessed The first hypothesis was AI has significant and positive impact on
through HTMT ratio (Heterotrait-Monotrait Ratio). HTMT is cyber security where it was found that since the P-value was
another new method of assessing the discriminant validity in 0.000 therefore, there exists a significant impact. Next was, expert
PLS, SEM method that forms the basis for model evaluation and system has significant and positive impact on artificial intelligence
assessment. The HTMT ratio needs to be 0.90 and any variable that where it was found that since the P-value was 0.492 therefore,
has values exceeding benchmark of 0.90 indicate that the variables there exists no significant impact because the P value should be
are not accurate conceptually or statistically. As shown in Table 2 less than 0.05. Next was, intelligent agents have significant and
above, all the values obtained of HTMT are less than 0.90 which positive impact on artificial intelligence and since the P-value
means that all variables and sub-variables are accurate conceptu- was 0.000 therefore, a significant and positive impact was found.
ally and statistically. The purpose of applying these test were to Furthermore, neural nets have significant and positive impact
ensure that reflective constructs of this article has strong relation- on artificial intelligence and since the P-value obtained was
ship or association with its indicators in the path model [39]. 0.017 and less than 0.05 therefore, there is a significant relation-
ship. Next was expert system which has impact over artificial intel-
3.3. Basic model ligence and cyber security and it obtained P-value of 0.493 which is
greater than 0.05 hence, there is no relationship between these
The model analysis of this article includes the independent vari- variables. The next variable was intelligence agents with artificial
ables that are expert system, neural nets and intelligence agents intelligence and cyber security which obtained P value of 0.000.
along with mediating variable that was AI and dependent variable Similarly, the relationship between neural nets, AI and cyber secu-
that was cyber security. The tables below show the model signifi- rity had 0.018 therefore, a strong and positive impact was
cance as well as important characteristics of the model. observed.
The Table 3 above shows that the model has R square value as
0.238 and 0.636 of AI and cyber security respectively. On the other
hand, the adjusted R square values are 0.233 and 0.635 of AI and 4. Discussion
cyber security respectively. This indicates that R square adjusted
is used for evaluating any discrepancies or errors in data or results The overall results of the study indicated that AI has become
whereas, R square values show the variations in the data caused by one of the primary assets for firms to improve their performance
the independent variables in the dependent variables. in terms of cyber security. The prevailing situation has revealed
The next Table 4 above shows the coefficients of the model. that cyber security is one of the important aspects for every organ-
Since the research has a mediating variable too therefore, the table isation to ensure because there are chances of large data and con-
above shows the significance values (P-value) as well. The standard fidential information to be attacked by online hackers. With the
value of P shows that the desired results should be less than 0.05 advancement of technology and rapid globalisation, the personal
(P < 0.05) in order to indicate it as significant. Any value exceeding and financial information of firms are stored on cloud and due to
it is considered to be insignificant and has not relationship. As the increased dependence on digital technology, cyber-attacks
shown above, the P value for AI with cyber security is 0.000 which have become common. The findings of the study revealed that all
is highly significant. Following this is, expert system, intelligence independent variables had significant and positive relation apart
agents and neural agent’s significance values that are 0.492, from expert system. Though many other researchers believe that
0.000 and 0.017 respectively. Out of all these values only, expert expert system is also essential but since the majority opinion does
system does not have a relationship with artificial intelligence not support in this study hence, significant results are not
whereas, remaining have. obtained.

3.4. Hypothesis assessment 4.1. Limitation and future implication

The hypothesis assessment is the next important stage of anal- There are many limitations faced by the researcher while con-
ysis that needs to be undertaken. After carrying out all necessary ducting this study. One of the primary issues was accessibility
tests for determining the relationship between variables and their and sample size of respondents. Due to current COVID situation,

Table 2
Discriminant Validity.

Artificial Intelligence Cyber Security Expert System Intelligent Agents Neural Nets
Artificial Intelligence
Cyber Security 0.889
Expert System 0.350 0.440
Intelligent Agents 0.529 0.585 0.730
Neural Nets 0.413 0.562 0.684 0.625

4
B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al. Materials Today: Proceedings xxx (xxxx) xxx

Table 4
Model Coefficients.

Sample Mean (M) Standard Deviation (STDEV) T Statistics (|O/STDEV|) P Values

Artificial Intelligence -> Cyber Security 0.797 0.023 34.668 0.000
Expert System -> Artificial Intelligence 0.041 0.065 0.688 0.492
Intelligent Agents -> Artificial Intelligence 0.411 0.062 6.607 0.000
Neural Nets -> Artificial Intelligence 0.164 0.068 2.390 0.017

Table 5
[3] K. Huang, C. Zhou, Y.-C. Tian, S. Yang, Y. Qin, Assessing the physical impact of
Hypothesis Assessment.
cyberattacks on industrial cyber-physical systems, IEEE Trans. Ind. Electron. 65
S. Hypothesis Sig- Result (10) (2018) 8153–8162.
NO Value [4] M. Bada, J.R.C. Nurse, The social and psychological impact of cyberattacks, in
Emerging Cyber Threats and Cognitive Vulnerabilities, Elsevier, 2020, pp. 73–
1 Artificial Intelligence -> Cyber Security 0.000 Accepted 92.
2 Expert System -> Artificial Intelligence 0.492 Rejected [5] M. Taddeo, Three ethical challenges of applications of artificial intelligence in
3 Intelligent Agents -> Artificial Intelligence 0.000 Accepted cybersecurity, Minds Mach. 29 (2) (2019) 187–191.
4 Neural Nets -> Artificial Intelligence 0.017 Accepted [6] K.R. Bhatele, H. Shrivastava, N. Kumari, The Role of Artificial Intelligence in
5 Expert System -> Artificial Intelligence -> Cyber 0.493 Rejected Cyber Security, in Countering Cyber Attacks and Preserving the Integrity and
Security Availability of Critical Systems, IGI Global, 2019, pp. 170–192.
6 Intelligent Agents -> Artificial Intelligence -> 0.000 Accepted [7] M. Conti, T. Dargahi, A. Dehghantanha, Cyber threat intelligence: challenges
and opportunities, Cyber Threat Intelligence, Springer (2018) 1–6.
Cyber Security
[8] S. Alshathry, Cyber attack on saudi aramco, Int. J. Manag., 11 (5) (2016).
7 Neural Nets -> Artificial Intelligence -> Cyber 0.018 Accepted
[9] S. Al Amro, Cybercrime in Saudi Arabia: fact or fiction?, Int. J. Comput. Sci.
Security
Issues 14 (2) (2017) 36.
[10] H.J. Mohammed, H.A. Daham, Analytic hierarchy process for evaluating
flipped classroom learning, Comput. Mater. Contin. 66 (3) (2021) 2229–
2239.
the researcher was not able to directly approach the respondents [11] H.J. Mohammed, I.A. M. Al-Jubori, M.M. Kasim, Evaluating project
but meetings were arranged and in small groups, the question- management criteria using fuzzy analytic hierarchy Process, AIP Conf. Proc.,
naires were filled. Secondly, the number of respondents were lim- 2138 (1) (2019) 040018(1–6).
[12] H.J. Mohammed, M.M. Kasim, I.N. Shaharanee, Selection of suitable e-learning
ited and in future, it is suggested that results can further be approach using TOPSIS technique with best ranked criteria weights, AIP Conf.
improved if more data is collected from large number of people. Proc., 1905 (2017) 040019(1–6).
Moreover, the researcher only focused on IT industry of Iraq and [13] H.J. Mohammed, M. Kasim, I.N. Shaharanee, Evaluation of e-learning
approaches using AHP- TOPSIS technique, J. Telecommun. Electron. Comput.
hence, the study was geographically limited therefore, for future, Eng. 10 (1–10) (2018) 7–10.
the studies can be improved if more comparison with other Middle [14] S. Hashemi, A. Marzuki, H.J. Mohammed, S. Kiumarsi, The effects of perceived
East countries are done or more variables are included in this study conference quality on attendees’ behavioural intentions, Anatolia 31 (3) (2020)
360–375.
for assessing the impact.
[15] T.S. Alshammari, H.P. Singh, Preparedness of Saudi Arabia to Defend Against
Cyber Crimes: An Assessment with Reference to Anti-Cyber Crime Law and GCI
Index, Arch. Bus. Res., 6 (12) (2018).
5. Conclusion [16] S.M. Ahmed, Artificial intelligence in Saudi Arabia: Leveraging
entrepreneurship in the Arab markets, 2019 Amity International Conference
on Artificial Intelligence (AICAI) (2019) 394–398.
Conclusively, it can be stated that the researcher carried out
[17] B. Alhayani, M. Rane, Face recognition system by image processing, Int. J.
quantitative based study with primary data collected from Electron. Commun. Eng. Technol. 5 (5) (2014) 80–90.
employees working in IT sector of Iraq. The hypothesis testing [18] B. Alhayani, H. Ilhan, Hyper spectral image classification using dimensionality
reduction techniques, Int. J. Innov. Res. Electr. Electron. Instrum. Control Eng. 5
was done and it was found that there is significant impact of intel-
(4) (2017) 71–74.
ligence agents and neural nets on AI. The advancement of technol- [19] B. Alhayani, A. Abdallah, Manufacturing intelligent corvus corone module for a
ogy has led towards increased data storage which requires more secured two way image transmission under WSN, Eng. Comput. 37 (9) (2020)
data security. 1–17.
[20] B. Alhayani, H. Ilhan, Visual sensor intelligent module based image
transmission in industrial manufacturing for monitoring and manipulation
problems, J. Intell. Manuf. 4 (2020) 1–14.
CRediT authorship contribution statement [21] M. Elhajji, A.S. Alsayyari, A. Alblawi, Towards an artificial intelligence
strategy for higher education in Saudi Arabia, in: 2020 3rd International
Bilal Alhayani: Conceptualization, Methodology, Software, Data Conference on Computer Applications & Information Security (ICCAIS), 2020,
pp. 1–7.
curation. Husam Jasim Mohammed: Visualization. Ibrahim [22] S. Zeadally, E. Adi, Z. Baig, I.A. Khan, Harnessing artificial intelligence
Zeghaiton Chaloob: Investigation, Supervision, Software. Jehan capabilities to improve cybersecurity, IEEE Access 8 (2020) 23817–
Saleh Ahmed: Validation, Writing - review & editing. 23837.
[23] I.Z. Chaloob, R. Ramli, M.K.M. Nawawi, A new multi-interval weights approach
in fuzzy goal programming for a multi-criteria problem, Int. J. Math. Oper. Res.
9 (2) (2016) 214–229.
Declaration of Competing Interest [24] I.Z. Chaloob, R. Ramli, M.K.M. Nawawi, Measuring economic and
environmental efficiency for agricultural zones in Iraq using data
The authors declare that they have no known competing finan- envelopment analysis, Int. J. Inf. Decis. Sci. 10 (3) (2018) 235–248.
[25] I.Z. Chaloob, R. Ramli, M.K.M. Nawawi, Using simulation and data envelopment
cial interests or personal relationships that could have appeared
analysis to evaluate Iraqi regions in producing strategic crops, AIP Conf. Proc.
to influence the work reported in this paper. 1635 (1) (2014) 525–529.
[26] E. Madhok, A. Gupta, N. Grover, Artificial Intelligence Impact on Cyber Security,
IITM J. Manag. IT 7 (1) (2016) 100–107.
References [27] A. Szychter, H. Ameur, A. Kung, H. Daussin, The Impact of Artificial Intelligence
on Security: a Dual Perspective, Taylor & Francis Taylor & Francis Group
[1] M. Komar et al., ‘‘High performance adaptive system for cyber attacks http://taylorandfrancis. com, 2018.
detection,” in 2017 9th IEEE International Conference on Intelligent Data [28] A. Anwar, S.I. Hassan, Applying artificial intelligence techniques to prevent
Acquisition and Advanced Computing Systems: Technology and Applications cyber assaults, Int. J. Comput. Intell. Res. 13 (5) (2017) 883–889.
(IDAACS), 2017, vol. 2, pp. 853–858. [29] H.J. Mohammed, M.M. Kasim, A.K. Hamadi, E.A. Al-Dahneem, Evaluating of
[2] J. White, Cyber Threats and Cyber Security: National Security Issues, Policy and collaborative and competitive learning using MCDM technique, Adv. Sci. Lett.
Strategies, Glob. Secur. Stud., 7 (4) (2016). 24 (6) (2018) 4084–4088.

5
B. Alhayani, H. Jasim Mohammed, I. Zeghaiton Chaloob et al. Materials Today: Proceedings xxx (xxxx) xxx

[30] H.J. Mohammed, M.M. Kasim, I.N. Shaharanee, Multi-criteria evaluation of e- [35] J.S. Ahmed, H.J. Mohammed, I.Z. Chaloob, Application of a fuzzy multi-
learning approaches, in Proceedings of the 6th International Conference on objective defuzzification method to solve a transportation problem, Mater.
Computing and Informatics, 2017, no. May. Today Proc. (2021).
[31] H.J. Mohammed, M.M. Kasim, E.A. AL-Dahneem, A.K. Hamadi, An analytical [36] H.A. Daham, H.J. Mohammed, An evolutionary algorithm approach for vehicle
survey on implementing best practices for introducing e-learning programs to routing problems with backhauls, Mater. Today Proc. (2021).
students, J. Educ. Soc. Sci., 5 (2) (2016) 191–196. [37] A. Magcale, D. Kekai, Artificial intelligence with cyber security, Google Patents
[32] K. Pal, R. Tiwari, S. Maheshwary, Implementation of artificial intelligence (2018).
methods to curb cyber assaults: A review, Int. Res. J. Eng. Technol. (2018) [38] N. Blaikie, Confounding issues related to determining sample size in
1466–1469. qualitative research, Int. J. Soc. Res. Methodol. 21 (5) (2018) 635–641.
[33] A. Panimalar, G. Pai, S. Khan, Artificial intelligence techniques for cyber [39] M.R. Ab Hamid, W. Sami, M.H.M. Sidek, Discriminant validity assessment: Use
security, Int. Res. J. Eng. Technol. 5 (3) (2018) 122–124. of Fornell & Larcker criterion versus HTMT criterion, J. Phys. Conf. Ser. 890 (1)
[34] H.J. Mohammed, E. AL-dahneem, A. Hamadi, A comparative analysis for (2017) 12163.
adopting an innovative pedagogical approach of flipped teaching for active
classroom learning, J. Glob. Bus. Soc. Entrep., 3 (5) (2016) 86–94.