See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/376375202

Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense

Strategies

Article in Journal Of Advanced Zoology · December 2023

CITATION READS

1 596

4 authors, including:

Badria Sulaiman Alfurhood Dattatreya Mankame

Princess Nora bint Abdul Rahman University SKSVMACET LAKSHMESHWAR
48 PUBLICATIONS 121 CITATIONS 10 PUBLICATIONS 120 CITATIONS

SEE PROFILE SEE PROFILE

Meenakshi Dwivedi
M.J.P. Rohilkhand University
10 PUBLICATIONS 1 CITATION

SEE PROFILE

All content following this page was uploaded by Meenakshi Dwivedi on 09 December 2023.

The user has requested enhancement of the downloaded file.

 Journal of Advanced Zoology
ISSN: 0253-7214
Volume 44 Issue S-2 Year 2023 Page 4715:4721

Artificial Intelligence and Cybersecurity: Innovations, Threats, and

Defense Strategies
Badria Sulaiman Alfurhood
Department of Computer Sciences, College of Computer and Information Sciences, Princess
Nourah bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia;
[email protected]
Dr. Dattatreya P Mankame
Department: Computer science and Business Systems Institute: Dayananda Sagar college of
Engineering District: Bangalore City: Bangalore State: Karnataka
Emailid: [email protected]
Dr Meenakshi Dwivedi
Designation: Assistant Professor Department: Department of B.Ed./M.Ed.
Institute: M.J.P. Rohilkhand University. District: Bareilly City: Bareilly State:UP
Email id [email protected]
Ms.Nidhi Jindal
Designation: Assistant Professor Department: Humanities
Institute:COER University District: Haridwar City: Roorkee/Haridwar
State: Uttrakhand
[email protected]
Article History Abstract: The application of artificial intelligence (AI) to cybersecurity has been examined
Received: 29 July 2023 in this study, which reveals a landscape characterized by innovations, difficulties, as well as
transformative potential. Looking into modern AI applications shows that deep learning
Revised: 28 October 2023
models—most notably recurrent neural networks—dominate in threat detection. Empirical
Accepted: 06 November 2023 data demonstrates AI's remarkable effectiveness in threat analysis in real-time, enabling
quick response protocols. Notwithstanding, obstacles like comprehensibility and
vulnerability to hostile assaults underscore the necessity for additional investigation.
Establishing explainable AI methods and strengthening defenses against hostile attacks are
two recommendations. In the future, research must concentrate on improving AI models for
interpretability and investigating cutting-edge tactics for robust cybersecurity against
changing threats.
CC License Keywords: Artificial Intelligence, Cybersecurity, Threat Detection, Deep Learning,
CC-BY-NC-SA 4.0 Adversarial Attacks

I: INTRODUCTION essential tools for real-time cyber threat detection and

A. Research background mitigation. This flexibility has become essential for
Artificial Intelligence (AI) has become increasingly fending off the ever-evolving strategies used by
prevalent in cybersecurity in recent years, resulting in malevolent actors [2]. Organizations using AI to
a paradigm shift in defensive strategies against strengthen their cybersecurity posture must
evolving cyber threats. Because cyber threats are comprehend the complex interactions between
constantly changing as well as digital landscapes are cutting-edge technologies as well as the ever-
becoming more complex, organizations are changing threat landscape in order to come up with
depending progressively more on AI-driven defence strategies that are both resilient and flexible.
technologies to strengthen their defenses [1]. This study explores this pivotal point and aims to
Machine learning algorithms, and pattern recognition, clarify the complex relationships between
in addition to predictive analytics, have become

4715
Available online at: https://jazindia.com
Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

cybersecurity and AI in order to generate more robust detection and response to fraudulent activity in
and efficient digital defence systems. endpoint security solutions [5]. This section explores
B. Research aim and objectives the particular uses of AI in cybersecurity, elucidating
Aim: the complexities of these technologies along with the
The aim of this study is to investigate artificial way they support digital defence tactics.
intelligence's (AI) incorporation in cybersecurity
from a broad perspective, looking at the way it
affects defence strategies, and response mechanisms,
alongside threat detection.
Objectives:
● To examine the latest cybersecurity
implications of AI.
● To evaluate the efficacy of threat detection
as well as mitigation powered by AI.
● To investigate the adaptable nature of
Figure 1: Current AI Applications in Cybersecurity
defence plans in light of changing cyber
B. Effectiveness of AI-Driven Threat Detection and
threats.
Mitigation
● To determine any potential drawbacks and
In contemporary cybersecurity, the efficacy of AI-
restrictions related to AI in cybersecurity.
driven threat detection and mitigation is crucial. With
C. Research Rationale
access to large datasets, machine learning algorithms
The growing use of artificial intelligence (AI) in
demonstrate an extraordinary capacity to recognize
cybersecurity calls for a careful examination of its
and categorize a variety of cyber threats, from
implications, including potential benefits and
malware to highly skilled phishing attacks [6].
difficulties. It is becoming increasingly important for
Specifically, deep learning models are very good at
people to understand the reasoning behind the
determining irregularities as well as intricate patterns,
adoption of AI-driven defenses as businesses heavily
which makes threat detection quick and precise. AI-
invest in them in order to ward off sophisticated
enabled real-time network traffic analysis improves
cyberattacks [3]. In order to highlight the strategic
the capacity to quickly detect and neutralize possible
benefits that artificial intelligence (AI) provides, this
threats, which significantly shortens response times
study aims to understand the motivations behind
[7]. Furthermore, AI-driven threat intelligence makes
cybersecurity's dependence on AI. By exploring the
use of global threat landscapes and historical data in
justification, the research hopes that it can provide a
order to foresee and proactively counter new cyber
comprehensive grasp of why artificial intelligence
threats. Automation, a fundamental component of
(AI) is considered essential in today's cybersecurity
artificial intelligence, plays a major role in threat
environments, guiding future developments while
mitigation by coordinating responses at machine
promoting a proactive strategy for digital defence.
speed. By contextualizing threat data and
II: LITERATURE REVIEW
differentiating between real and false threats, context-
A. Current AI Applications in Cybersecurity
aware AI systems reduce the possibility of missing
Present-day artificial intelligence (AI) applications
important security incidents [8]. In order to clarify
have become crucial for strengthening digital defense
the practical impact of these technologies on boosting
systems in the field of cybersecurity. The utilization
the general durability of cybersecurity frameworks,
of machine learning algorithms, specifically deep
this section critically evaluates the empirical data as
learning models, is imperative in the identification of
well as case studies pertaining to the effectiveness of
threats as well as anomaly detection processes, as it
AI in threat detection and mitigation.
improves the capacity to spot unknown threats.
Furthermore, large-scale datasets can be parsed more
easily with the help of natural language processing,
which makes it easier to extract useful information
from unstructured data [4]. Organizations can
proactively strengthen vulnerabilities prior to
exploitation with the assistance of AI-driven
predictive analytics, which provides anticipatory
threat intelligence. Artificial intelligence (AI)
automates repetitive security tasks, freeing up Figure 2: Effectiveness of AI-Driven Threat Detection and
Mitigation
cybersecurity experts to concentrate on more difficult
problems. AI integration also improves real-time
4716
Available online at: https://jazindia.com
Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

C. Adaptability of Defense Strategies to Evolving There is a clear literature gap regarding the long-term
Cyber Threats effects of AI-driven defense strategies, regardless of
In the dynamic field of cybersecurity, defense the wealth of research on the application of AI in
strategies must be able to adapt to changing cyber cybersecurity. There is a lack of thorough research
threats. Artificial intelligence (AI), which offers a addressing the socio-economic, ethical, as well as
flexible and adaptable framework, is indispensable legal aspects of this integration, despite the fact that
for bolstering defences. Security measures can adjust current literature explores the technical aspects of AI
in real-time thanks to machine learning algorithms, applications [13]. The absence of research in the
which are constantly learning from changing threat literature emphasizes the need for a comprehensive
patterns. AI-powered dynamic threat modelling investigation that goes beyond the technical
makes it possible to quickly identify new attack effectiveness of AI in cybersecurity alongside
vectors while developing countermeasures [9]. One emphasizes the larger organizational and societal
important application is behavioral analytics, which ramifications that influence how digital defense
keeps an eye out for abnormalities in user and system mechanisms develop in the future.
behavior. This helps identify new threats that III: METHODOLOGY
traditional signature-based techniques might The research methodology utilized in this study is
overlook. AI integration with security-related consistent with the interpretivism philosophy, with
information and event management (SIEM) systems the goal of understanding cybersecurity as well as
also makes it easier to correlate data from various artificial intelligence (AI) interactions from a
sources, providing a comprehensive picture of contextualized and sophisticated standpoint. In the
possible threats. AI-driven defence mechanisms' field of AI-driven cybersecurity, the deductive
adaptive nature guarantees that security plans change method is used to methodically test theories and
in tandem with the sophistication of cyberattacks, frameworks that are currently in place [14]. In order
narrowing the window of vulnerability [10]. This to give a thorough explanation of the state, traits, as
section examines the manner in which AI makes well as implications of AI applications in
defense strategies more flexible and proactive when cybersecurity, a descriptive research design is used.
dealing with new and developing cybersecurity Meaningful insights can be extracted from the subject
threats. matter through a thorough exploration made possible
D. Challenges and Limitations in AI-Enhanced by this design.
Cybersecurity The foundation of this research is gathering
Although artificial intelligence (AI) holds great additional information, which makes use of credible
promise for improving cybersecurity, there are industry reports, peer-reviewed journals, conference
significant obstacles and constraints that require to be proceedings, and already published scholarly
carefully considered. The interpretability of AI- literature. The dataset includes a wide range of
driven security models is a major worry since deep sources, from case studies explaining the real-world
learning algorithms' intrinsic complexity can make it applications of artificial intelligence in cybersecurity
difficult to comprehend the way decisions are made. scenarios to scholarly publications on machine
Another significant issue is adversarial attacks, in learning algorithms in identifying threats [15]. The
which skilled adversaries try to trick and control the analysis is enhanced with practical considerations as
procedure for learning by taking advantage of well as real-world implementations thanks to the
weaknesses in AI systems [11]. Furthermore, AI extensive inclusiveness of technical documents, and
models' reliance on historical data could result in a whitepapers, followed by reports from cybersecurity
delay in recognizing novel threats, which would companies. To synthesize current knowledge on AI
make it more difficult to properly counter zero-day applications in cybersecurity, a thorough literature
attacks. One major obstacle that affects its capacity to review needs to be carried out, which serves as the
generalize models throughout different and dynamic foundation for the creation of a conceptual
threat landscapes is the lack of designated data sets framework. This framework incorporates proven
for training AI models in the cybersecurity domain theories and models that are pertinent to the
[12]. Other issues that come up are ethical ones, like challenges, adaptability, as well as efficacy of
the possibility of privacy violations and bias in AI defense strategies driven by artificial intelligence
algorithms. This section looks critically at these [16]. A theoretical foundation that will eventually be
obstacles as well as constraints, offering insights into empirically tested against real-world scenarios is
the subtle aspects that require to be taken into formed by the deductive approach, which directs
consideration for the ethical and successful towards the recognition of important variables and
integration of AI in cybersecurity frameworks. relationships within the literature.
E. Literature Gap
4717
Available online at: https://jazindia.com
Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

Utilizing content analysis methods, the technical take proactive measures to patch security flaws. One
analysis draws patterns, trends, as well as recurrent of the key elements in this effectiveness is the real-
themes from the enormous amount of secondary data time network traffic analysis made possible by AI
that has been gathered. Technical details are given algorithms [20]. With the help of this capability,
special consideration, including the algorithms used organizations can quickly detect abnormalities in the
in AI-driven threat detection, the effectiveness of digital ecosystem and initiate automated response
machine learning models in real-time response, in protocols. AI-driven real-time analysis's quickness
addition to the defense strategies' adaptability to and responsiveness are crucial for minimizing
various cyber threats. response times, which lessens the possible impact of
By cross-referencing data from several sources cyber threats. Moreover, recurrent neural networks
followed by viewpoints, a rigorous triangulation (RNNs), in particular, show great promise for
process is used to guarantee the validity and advanced persistent threat prediction alongside
reliability of the findings. Moreover, the mitigation [21]. RNNs' flexibility and capacity for
incorporation of reports from credible cybersecurity learning add to their transformative potential,
organizations in addition to peer-reviewed academic strengthening cybersecurity frameworks' proactive
journals strengthens the data's authority and adds to defense posture. By combining cutting-edge machine
the research outcomes' resilience [17]. This learning techniques, AI is now seen as an essential
methodological approach seeks to offer a thorough as collaborator in strengthening digital defenses,
well as technically sound investigation of AI signaling an important change in the direction of
applications in cybersecurity, providing insightful cybersecurity tactics that are more adaptable and
information about the challenges, performance, and resilient.
adaptability of AI-driven defense strategies. C. Defense Plans' Flexibility to Change in Response
IV: RESULTS to New Threats
A. AI Applications in Cybersecurity: Current One important and dynamic theme that highlights the
Situation transformative potential of Artificial Intelligence (AI)
The investigation of AI uses in cybersecurity reveals in countering emerging cyber threats is the
a changing environment characterized by the spread adaptability of defense strategies in the setting of
of cutting-edge machine learning methods. Threat cybersecurity. AI-driven models, which have the
detection systems heavily rely on deep learning capacity to dynamically learn and change in real-
models, specifically Convolutional Neural Networks time, are essential to this adaptability [22]. This
(CNNs) as well as Recurrent Neural Networks responsiveness is essential given the constantly
(RNNs). CNNs are incredibly effective at changing strategies used by malevolent actors in the
recognizing threats from images. They are also very digital sphere. In this adaptability paradigm, AI-
good at recognizing malware based on visual facilitated dynamic threat modeling appears to be
patterns. RNNs, on the contrary, are excellent at crucial. Artificial Intelligence (AI) can quickly detect
analyzing network traffic temporally, which makes it new attack patterns that could potentially evade
possible to identify minute patterns that point to conventional, static defense mechanisms by utilizing
sophisticated cyber threats [18]. Through the analysis machine learning algorithms as well as pattern
of textual data, the incorporation of Natural recognition [23]. This ability enables cybersecurity
Language Processing (NLP) techniques strengthens professionals to stay ahead of evolving threats by
defenses against malicious communications as well facilitating the swift creation of countermeasures.
as phishing attacks, thereby further improving Furthermore, defenses become more adaptive when
cybersecurity. AI is incorporated into the management of security
B. Efficacy of AI-Driven Threat Detection and information and events (SIEM) systems. AI-enabled
Mitigation SIEM systems provide cybersecurity professionals
The empirical data that was obtained through a with a comprehensive view of potential threats by
thorough examination of case studies and real-world analyzing large and diverse datasets [24]. By
applications demonstrates the strong effectiveness of facilitating quick and well-informed decision-
AI-driven threat detection and mitigation in the field making, this improved situational awareness makes it
of cybersecurity. After being extensively trained on a possible to respond proactively to possible threats.
variety of datasets, machine learning models have Fundamentally, AI-enabled defense strategies'
been fine-tuned in order to demonstrate an amazing adaptability signals a paradigm shift in cybersecurity.
capacity to recognize and differentiate complex By utilizing machine learning in addition to dynamic
patterns that are indicative of malicious activity [19]. threat modeling, it surpasses conventional rule-based
Because of this increased accuracy, potential threats methods and offers a strong defense framework that
can be identified earlier, allowing organizations to can quickly respond to as well as neutralize new
4718
Available online at: https://jazindia.com
Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

cyber threats in the quickly changing digital

environment of today.

Figure 3: Adaptability of Defense Strategies to Evolving Threats

D. Limitations in AI-Enhanced Cybersecurity
Research on the application of artificial intelligence Figure 4: Use of AI in Cybersecurity
(AI) to cybersecurity reveals a number of obstacles In conclusion, the technical depth of the findings
and restrictions that must be carefully taken into highlights the revolutionary potential that AI can
account when implementing these cutting-edge have in strengthening cybersecurity's digital defenses.
technologies. The most significant of these A picture of improved cyber resilience has been
difficulties is the interpretability problem, which generated by the combination of cutting-edge
proves to be an enormous obstacle. Deep learning machine learning techniques, dynamic defense
models are very effective, but their complex strategies, and real-time threat analysis. However
decision-making processes make it more difficult to acknowledging the difficulties and constraints
understand why they do what they do [25]. It is highlights how crucial it is to deal with these aspects
crucial to close this gap for successful integration in order to deploy AI responsibly as well as
because cybersecurity professionals find it difficult to effectively in practical cybersecurity frameworks.
comprehend and have confidence in the decisions
made by AI systems because of their absence of Themes Key Points
interpretability. In the context of AI-driven Current - Dominance of CNNs and RNNs
cybersecurity, adversarial attacks stand out as a major Landscape of in image-based threat recognition
concern. AI systems have vulnerabilities that AI and temporal analysis of network
malicious actors take advantage of in order to abuse Applications traffic, respectively.
them and produce results that are erroneous or - Integration of NLP techniques
compromised. This emphasizes the significance it is for fortifying defences against
to having strong security measures in place to protect phishing attacks and analyzing
these technologies from manipulation by adversaries textual data.
[26]. Maintaining the reliability of automated threat
Efficacy of
detection and response systems depends critically on
AI-Driven - Machine learning models exhibit
the integrity of AI algorithms. Moreover, there is a
Threat remarkable capacity in discerning
significant limitation introduced by the utilization of
Detection & patterns indicative of malicious
historical data. While AI systems are excellent at
Mitigation activities.
recognizing patterns in historical data, they might
- Real-time analysis of network
have trouble spotting new and unseen threats called
traffic enables swift identification
"zero-day threats." Because of this possible detection
of anomalies and initiation of
lag, training datasets must be updated frequently to
automated responses.
keep AI models adaptable and prepared to identify
- Deep learning models, especially
new threats quickly. In the dynamic and changing
RNNs, showcase promise in
field of cybersecurity, ongoing monitoring,
predicting and mitigating
assessment, alongside improvement of AI algorithms
advanced persistent threats.
become crucial to preserving optimal threat detection
capabilities [27]. In order to fully utilize AI to Adaptability
improve cybersecurity while preserving the strength of Defence - Dynamic learning capabilities of
and adaptability of defense mechanisms against Strategies & AI-driven models allow for
sophisticated threats, it is imperative that these issues Evolving continuous adaptation to emerging
be resolved. Threats cyber threats.

4719
Available online at: https://jazindia.com
Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

- Dynamic threat modelling In the future, a number of focused research directions

facilitates rapid development of can greatly advance the application of artificial
countermeasures against novel intelligence (AI) in cybersecurity. First, in order to
attack patterns. overcome the interpretability problem, research
- Integration of AI into SIEM should concentrate on creating cybersecurity-specific
systems enhances the adaptability explainable AI (XAI) methods. Investigating
of defences by providing a techniques that improve the process of decision-
comprehensive view of threats. making transparency in deep learning models would
Challenges encourage trust among cybersecurity experts and
and - Interpretability challenges due to make it possible for efficient cooperation between AI
Limitations in the complex decision-making systems and human analysts. Secondly, protecting AI
AI-Enhanced processes of deep learning systems from hostile attacks is a crucial area of
Cybersecurity models. research. AI model vulnerabilities can be reduced by
looking into strong adversarial training strategies as
- Adversarial attacks underscore well as anomaly detection methods tailored to
the need for robust security cybersecurity scenarios [29]. Furthermore, to ensure
measures to safeguard AI systems. the dependability and resilience of AI-driven
- Reliance on historical data may cybersecurity defences, proactive strategies for
introduce a lag in identifying foreseeing as well as neutralizing adversarial
zero-day threats, requiring attempts must be developed through interdisciplinary
continual updates to datasets. research collaboration between computer scientists
V: EVALUATION AND CONCLUSION followed by cybersecurity experts. These research
A Critical Evaluation suggestions seek to improve the field by offering
The research findings critical evaluation reveal the workable solutions in addition to addressing current
subtle challenges as well as the revolutionary issues. Future research can significantly contribute to
potential of integrating artificial intelligence (AI) the responsible and productive integration of AI in
with cybersecurity. Positively, the empirical data cybersecurity frameworks by exploring the nuances
highlights the noteworthy effectiveness of threat of interpretability as well as fortification against
detection and mitigation powered by AI. Recurrent adversarial threats.
neural networks in particular, which are machine C Future work
learning models, demonstrate remarkable accuracy in Subsequent research in this field ought to be
identifying complex patterns linked to malicious concentrated on improving the interpretability of AI
activity. AI algorithms enable real-time network models to guarantee open decision-making
traffic analysis, which improves an organization's procedures. Furthermore, research should concentrate
capacity to proactively counteract transforming cyber on creating cutting-edge defences against dynamic
threats. Nonetheless, significant issues regarding adversarial threats for AI-driven cybersecurity [30].
interpretability arise since deep learning models' The next generation of resilient alongside adaptive
intricate decision-making procedures make it cybersecurity frameworks is expected to be shaped in
challenging to comprehend their reasoning [28]. large part by research into the intersection of AI and
Strong security measures are essential because AI quantum computing as well as cutting-edge methods
systems are highly susceptible to hostile attacks. for integrating threat intelligence in real-time.
Additionally, relying solely on historical data may REFERENCE
cause a delay when identifying zero-day threats, [1] Bonfanti, M.E., 2022. Artificial intelligence and the offence-
requiring training datasets to be updated on a regular defence balance in cyber security. Cyber Security: Socio-
Technological Uncertainty and Political Fragmentation. London:
basis. In summary, the critical evaluation highlights Routledge, pp.64-79.
the significance of resolving interpretability issues, [2] Das, R. and Sandhane, R., 2021, July. Artificial intelligence in
strengthening defences against adversarial cyber security. In Journal of Physics: Conference Series (Vol.
manipulation, and developing tactics to improve AI 1964, No. 4, p. 042072). IOP Publishing.
[3] Jun, Y., Craig, A., Shafik, W. and Sharif, L., 2021. Artificial
models' resilience to new threats, despite the fact that intelligence application in cybersecurity and cyberdefense.
AI offers a potent tool for enhancing cybersecurity. Wireless Communications and Mobile Computing, 2021, pp.1-10.
This sophisticated understanding serves as the [4] Bécue, A., Praça, I. and Gama, J., 2021. Artificial intelligence,
cornerstone of an all-encompassing and practical cyber-threats and Industry 4.0: Challenges and opportunities.
Artificial Intelligence Review, 54(5), pp.3849-3886.
strategy for maximizing AI's advantages in [5] Soni, V.D., 2020. Challenges and Solution for Artificial
cybersecurity while manoeuvring its inherent Intelligence in Cybersecurity of the USA. Available at SSRN
complexities. 3624487.
B Research recommendation
4720
Available online at: https://jazindia.com
 Artificial Intelligence and Cybersecurity: Innovations, Threats, and Defense Strategies

[6] Alhayani, B., Mohammed, H.J., Chaloob, I.Z. and Ahmed, J.S., [19] Safitra, M.F., Lubis, M. and Fakhrurroja, H., 2023.
2021. Effectiveness of artificial intelligence techniques against Counterattacking cyber threats: A framework for the future of
cyber security risks apply of IT industry. Materials Today: cybersecurity. Sustainability, 15(18), p.13369.
Proceedings, 531. [20] Johnson, J., 2019. Artificial intelligence & future warfare:
[7] Parisi, A., 2019. Hands-On Artificial Intelligence for implications for international security. Defense & Security
Cybersecurity: Implement smart AI systems for preventing cyber Analysis, 35(2), pp.147-169.
attacks and detecting threats and network anomalies. Packt [21] Dash, B., Ansari, M.F., Sharma, P. and Ali, A., 2022. Threats
Publishing Ltd. and Opportunities with AI-based Cyber Security Intrusion
[8] Lakhani, A., 2023. AI Revolutionizing Cyber security Detection: A Review. International Journal of Software
unlocking the Future of Digital Protection. Engineering & Applications (IJSEA), 13(5).
[9] Şeker, E., 2019. Use of Artificial Intelligence [22] Chakraborty, A., Biswas, A. and Khan, A.K., 2023. Artificial
Techniques/Applications in Cyber Defense. arXiv preprint intelligence for cybersecurity: Threats, attacks and mitigation. In
arXiv:1905.12556. Artificial Intelligence for Societal Issues (pp. 3-25). Cham:
[10] Radanliev, P., De Roure, D., Maple, C. and Ani, U., 2022. Springer International Publishing.
Super-forecasting the ‘technological singularity’risks from [23] Kyrkou, C., Papachristodoulou, A., Kloukiniotis, A.,
artificial intelligence. Evolving Systems, 13(5), pp.747-757. Papandreou, A., Lalos, A., Moustakas, K. and Theocharides, T.,
[11] Chomiak-Orsa, I., Rot, A. and Blaicke, B., 2019, August. 2020, July. Towards artificial-intelligence-based cybersecurity for
Artificial intelligence in cybersecurity: the use of AI along the robustifying automated driving systems against camera sensor
cyber kill chain. In International Conference on Computational attacks. In 2020 IEEE computer society annual symposium on
Collective Intelligence (pp. 406-416). Cham: Springer VLSI (ISVLSI) (pp. 476-481). IEEE.
International Publishing. [24] Schmidt, E., Work, B., Catz, S., Chien, S., Darby, C., Ford,
[12] Gupta, S., Sabitha, A.S. and Punhani, R., 2019. Cyber security K., Griffiths, J.M., Horvitz, E., Jassy, A., Mark, W. and Matheny,
threat intelligence using data mining techniques and artificial J., 2021. National security commission on artificial intelligence
intelligence. Int. J. Recent Technol. Eng, 8, pp.6133-6140. (ai). National Security Commission on Artificial Intellegence,
[13] Dhoni, P.S. and Kumar, R., 2023. Synergizing Generative AI Tech. Rep.
and Cybersecurity: Roles of Generative AI Entities, Companies, [25] Zeadally, S., Adi, E., Baig, Z. and Khan, I.A., 2020.
Agencies, and Government in Enhancing Cybersecurity. Harnessing artificial intelligence capabilities to improve
[14] Mathew, A., 2021. Artificial intelligence for offence and cybersecurity. Ieee Access, 8, pp.23817-23837.
defense-the future of cybersecurity. Educational Research, 3(3), [26] Lin, T.C., 2019. Artificial intelligence, finance, and the law.
pp.159-163. Fordham L. Rev., 88, p.531.
[15] Buchanan, B., 2020. A national security research agenda for [27] Alkali, Y., Routray, I. and Whig, P., 2022. Study of various
cybersecurity and artificial intelligence. Cent. Secur. Emerg. methods for reliable, efficient and Secured IoT using Artificial
Technol. Issue Brief, 7. Intelligence. Available at SSRN 4020364.
[16] Zhou, Z., Kuang, X., Sun, L., Zhong, L. and Xu, C., 2020. [28] Pandey, A.B., Tripathi, A. and Vashist, P.C., 2022. A survey
Endogenous security defense against deductive attack: When of cyber security trends, emerging technologies and threats. Cyber
artificial intelligence meets active defense for online service. IEEE Security in Intelligent Computing and Communications, pp.19-33.
Communications Magazine, 58(6), pp.58-64. [29] Ruan, J., Liang, G., Zhao, J., Zhao, H., Qiu, J., Wen, F. and
[17] Samtani, S., Kantarcioglu, M. and Chen, H., 2020. Dong, Z.Y., 2023. Deep learning for cybersecurity in smart grids:
Trailblazing the artificial intelligence for cybersecurity discipline: Review and perspectives. Energy Conversion and Economics, 4(4),
a multi-disciplinary research roadmap. ACM Transactions on pp.233-251.
Management Information Systems (TMIS), 11(4), pp.1-19. [30] Zhang, Z., Al Hamadi, H., Damiani, E., Yeun, C.Y. and
[18] Sarma, M., Matheus, T. and Senaratne, C., 2021. Artificial Taher, F., 2022. Explainable artificial intelligence applications in
Intelligence and Cyber Security: A New Pathway for Growth in cyber security: State-of-the-art in research. IEEE Access.
Emerging Economies via the Knowledge Economy?. In Business
Practices, Growth and Economic Policy in Emerging Markets (pp.
51-67).

4721
Available online at: https://jazindia.com

View publication stats