Addressing IoT Security Challenges Through AI Solutions
Addressing IoT Security Challenges Through AI Solutions
Md Shihab Uddin
School of Engineering
San Francisco Bay University
Fremont, CA 94539
50
International Journal of Computer Applications (0975 – 8887)
Volume 186 – No.45, October 2024
most nodes in an IoT network have limited resources, they are this layer include node authentication, weak encryption, and
often targeted by hackers. Various solutions have been access control [24]. Unfortunately, privacy attacks and crimes
proposed to address IoT network security and privacy targeting the perception layer are prevalent in real-world
concerns, most of which rely on standard cryptographic scenarios. One common attack method involves taking control
protocols. However, these existing solutions are insufficient for of a node. Other techniques include the use of malicious code,
addressing the unique security challenges posed by IoT data injection, replay attacks, and side-channel attacks. For
networks. By incorporating machine learning (ML) and deep instance, if an attacker gains control of a node, it may cease to
learning into IoT devices and networks, many threats to IoT transmit valid network data and could even disable the IoT
security can be mitigated. security software. If the IoT application receives corrupted data
or is compromised by malicious code injection, it may not
The current IoT opportunities in the healthcare sector are function as intended. Eavesdropping, also known as sniffing or
promising, especially due to its sensing and measuring snooping, is a technique where an attacker intercepts and
capabilities, including the low-energy form of narrowband IoT. examines data exchanged between two devices [25]. In an IoT
This technology is popular in the healthcare field because of its network, a replay attack involves repeatedly falsifying,
low energy usage. Several concepts exist for using narrowband altering, or reusing the identities of related objects. Given
IoT in the healthcare industry. Narrowband IoT has become sufficient time and access to encryption keys, an attacker can
widely used and is compatible with cellular networks like LTE. also perform a timing attack. These are just a few examples of
As a result, narrowband IoT has recently emerged as a viable the numerous ways vital information can be compromised
choice for healthcare-related applications [15]. The IoT risk beyond direct node attacks [26].
management model in healthcare is presented in Figure 1.
Table 1: IoT Key Issues
Ref. IoT key issues Advantages
[34] Quality of service Involves managing data
(QoS) traffic load and protocols
across all layers in IoT
architecture, including
routine checks for QoS
(Quality of Service) and QoE
(Quality of Experience).
[35] Authentication Focuses on addressing issues
Figure 1: The IoT risk management model in healthcare
and identification related to IoT integrations
[16].
with internet protocols
. (IPv6), as well as
authentication and
identification issues.
[36] Environment, Discusses the incorporation
power, and energy of green technology in IoT,
the design of low-power-
consumption devices and
chips, and aspects of
pollution control and
management.
[37] Reliability Covers connectivity,
mobility, and routing issues,
along with the reliability of
Figure 2: Potential economic impact of dominant IoT infrastructure and IoT
applications by 2025 [22] applications.
[38] Scalability Discusses the challenges of
3. SECURITY ISSUES IN THE SENSING scaling IoT solutions across
LAYER large platforms and
A typical IoT architecture is composed of three main layers: the geographical locations,
application layer, the network layer, and the perception layer including potential discovery
[23]. However, as the importance of data processing and services.
intelligent decision-making continues to grow, the support or
middleware layer between the network and application layers
has become increasingly crucial. IoT systems can include
multiple layers, such as a network layer and a support layer. In
4. SECURITY ISSUES IN THE
many studies on IoT systems, cloud computing has been MIDDLEWARE OR SUPPORT LAYER
utilized as the underlying support layer. Distributed computing solutions have been used to replace
centralized cloud environments in a variety of cases, with good
The perception layer, also known as the sensing layer, results in terms of performance and response time. All sent data
comprises various sensors and devices. This layer is should now be checked for accuracy, concision, and secrecy.
characterized by limited storage, processing, memory, and When someone inside a network purposefully alters or steals
communication capabilities. The primary security measures in data or information, this is known as a malicious inside attack
51
International Journal of Computer Applications (0975 – 8887)
Volume 186 – No.45, October 2024
[29]. By inserting malicious SQL queries into the code, SQL happen. IoT devices in industrial settings are equipped with
injection attacks are used to steal data from user services in the various sensors that constantly monitor and gather data on the
real world. When damage to one virtual machine spreads to performance and condition of machinery, including parameters
another, this is a virtualization attack. With the help of cloud like temperature, vibration, and pressure. ML algorithms
malware injection, a hacker can take over a cloud service, analyze this extensive data to detect patterns and anomalies that
install malicious code, or even create a fake virtual machine. could indicate potential failures or malfunctions [42].
There could be significant consequences if attacks are so
powerful that cloud infrastructure is incredibly frustrated [30]. 6.3 Smart Home Security Systems
In the rapidly advancing consumer market, ML has become a
5. APPLICATION LAYER crucial technology for enhancing the security of smart home
Defining and maintaining IoT applications, including their devices. The integration of ML into home security systems is
interactions with specific clients, fall under the scope of the revolutionizing the management of security in residential
application layer. One way to use IoT services is through a user spaces. One of the primary applications of ML in this area is
interface. A computer, a smartphone, or any other Internet- through advanced facial recognition technologies. Unlike
enabled smart device could serve as an interface. The data that traditional security systems that rely on static passcodes or
the middleware layer process is used by the application layer keys, ML-powered systems can dynamically recognize the
[31]. This holds for a wide range of application categories, faces of residents and frequent visitors, offering a more
including applications for smart homes, smart cities, industry, personalized and secure experience. These systems
construction, and health. The security needs of an application continuously learn and improve their accuracy over time by
may change depending on how it functions. When sending analyzing the various faces they encounter. Additionally, smart
information on climate change forecasts as opposed to when security systems can learn and understand regular household
conducting online banking, it is acceptable to expect a better patterns and routines, enabling them to detect anomalies or
level of security. The application layer must address various unusual activities, such as movement in an empty house or a
security challenges, such as attacks on access control, door being opened at an odd hour. This feature is particularly
malicious code, programming, data leaks, service interruptions, useful for monitoring elderly family members or securing the
application vulnerabilities, and software flaws [32]. Attacks home while away [43].
that interrupt service, commonly referred to as “Distributed
Denial of Service (DoS)” attacks, stop users from using IoT 6.4 Automotive Security
apps by sending a flood of requests to servers or networks. Connected vehicles represent a major advancement in the
Threat actors could use sniffer software to monitor data being automotive industry, integrating communication technologies
transmitted by IoT apps. Attacks that gain unauthorized access into vehicles. These technologies enable cars to communicate
can seriously harm a system quickly by preventing users from with each other (V2V - vehicle-to-vehicle), with infrastructure
using IoT-related services and wiping data [33-36]. (V2I - vehicle-to-infrastructure), and with other devices (V2X
- vehicle-to-everything), improving overall transportation
6. IoT SECURITY SOLUTIONS BASED efficiency, safety, and convenience. Beyond security, ML
ON ML algorithms can predict potential vehicle faults before they occur
ML is transforming IoT security by enabling real-time by analyzing historical data and identifying patterns that
monitoring of network traffic to detect anomalies that may typically precede equipment failures. This predictive
indicate security breaches. ML and DL models are also used for maintenance approach reduces the risk of malfunctions that
UAV detection [37, 38]. These models continuously analyze could be exploited by cyber threats. However, while ML
data patterns from connected devices, identifying deviations significantly enhances automotive security, it also presents
from typical behavior that could signal a cyber threat. This challenges, such as ensuring the privacy of collected data,
section reviews current trends in IoT security, presenting protecting against manipulation of ML models, and
specific examples and case studies that illustrate how ML maintaining regular updates to keep pace with evolving cyber
methodologies are applied in practical scenarios. threats [44].
52
International Journal of Computer Applications (0975 – 8887)
Volume 186 – No.45, October 2024
remain in their intended state throughout the supply chain. This [2] Y. Yu, J. Wang and G. Zhou, "The exploration in the
could involve monitoring for signs of tampering, damage, or education of professionals in applied Internet of Things
unauthorized access to the products [45, 46]. engineering", Proceedings of the 4th International
Conference on Distance Learning and Education
7. IoT SECURITY SOLUTIONS BASED (ICDLE), pp. 74-77, 2010.
ON DL [3] J. Li, Z. Huang and X. Wang, "Countermeasure research
Deep learning often employs multi-layer perceptrons (MLPs) about developing Internet of Things economy: A case of
and feed-forward artificial networks (FFANs). The traditional hangzhou city", Proceedings of the International
MLP architecture consists of three layers: the input layer, one Conference on E-Business and E-Government (ICEE),
or more hidden layers, and the output layer. In an AI network, 2011
each node in a layer is connected to a specific value in the
preceding layer, ultimately linking back to the input layer. [4] M. M. Hossain, M. Fotouhi and R. Hasan, "Towards an
During model training, MLP utilizes backpropagation to adjust Analysis of Security Issues, Challenges, and Open
the internal weight values [47]. This MLP network is applied Problems in the Internet of Things," 2015 IEEE World
to analyze the NSL-KDD dataset for malware detection, Congress on Services, New York, NY, USA, 2015, pp. 21-
explain IoT parameters, identify malicious traffic originating 28, doi: 10.1109/SERVICES.2015.12.
from IoT devices, and develop a model for intrusion detection
[5] Podder, P., Mondal, M., Bharati, S., & Paul, P. K. (2021).
[48].
Review on the security threats of internet of things. arXiv
Recurrent neural networks (RNNs) are another model type that preprint arXiv:2101.05614.
uses neural feed-forward networks but includes an internal state [6] Bharati, S., Podder, P., Mondal, M. R. H., & Paul, P. K.
or memory to manage sequential data effectively. This (2021). Applications and challenges of cloud integrated
characteristic makes RNNs particularly useful for IoT security, IoMT. Cognitive Internet of Medical Things for Smart
natural language processing, and speech recognition [49]. IoT Healthcare: Services and Applications, 67-85.
devices generate a significant amount of sequential data, such
as time-varying information and network traffic flows. The [7] Mondal, M. R. H., Bharati, S., Podder, P., &
recurrent connections in neural networks allow them to detect Kamruzzaman, J. (2023). Deep Learning and Federated
potential security vulnerabilities when a threat's Learning for Screening COVID-19: A Review.
communication patterns evolve over time. The RNN's ability to BioMedInformatics, 3(3), 691-713.
predict time series, supported by its long short-term memory [8] Hoque, K., Hossain, M. B., Sami, A., Das, D., Kadir, A.,
(LSTM), enables it to recall previous inputs. For instance, & Rahman, M. A. (2024). Technological trends in 5G
LSTM-based recurrent networks can be used to identify and networks for IoT-enabled smart healthcare: A review.
classify malicious applications and detect intrusions, along International Journal of Science and Research Archive,
with other security-related tasks [50]. 12(2), 1399-1410.
Various deep learning models and hybrid network models can [9] Bazgir, Ehsan, et al. "Security aspects in IoT based cloud
be employed to detect and prevent malware, spoofing, and computing." World Journal of Advanced Research and
computer virus attacks across a wide range of IoT devices [51]. Reviews 20.3 (2023): 540-551.
One such model is a deep belief network (DBN)-based security [10] Mazhar, T., Talpur, D.B., Shloul, T.A., Ghadi, Y.Y., Haq,
model, which can be used to safeguard IoT devices [52]. I., Ullah, I., Ouahada, K. and Hamam, H., 2023. Analysis
Researchers have explored multiple deep learning approaches, of IoT security challenges and its solutions using artificial
categorizing them as discriminative when human intervention intelligence. Brain Sciences, 13(4), p.683.
is required and generative when none is needed. Hybrid
systems may also be utilized when the data quality necessitates [11] Rawat, D.B.; Doku, R.; Garuba, M. Cybersecurity in Big
it [53-62]. Data Era: From Securing Big Data to Data-Driven
Security. IEEE Trans. Serv. Comput. 2019, 14, 2055–
8. CONCLUSION 2072.
This paper gives a review of the literature on IoT security [12] Farrokhi, A.; Farahbakhsh, R.; Rezazadeh, J.; Minerva, R.
awareness, focusing on the IoT model, IoT-based intelligent Application of Internet of Things and artificial
environments, and the security challenges addressed by intelligence for smart fitness: A survey. Comput. Netw.
machine learning solutions. We conducted an evaluation of the 2021, 189, 107859.
knowledge base surrounding IoT security intelligence,
[13] Yahya, F.; Zaki, A.F.A.; Moung, E.G.; Sallehudin, H.;
examining the IoT paradigm, smart environments built on IoT,
Bakar, N.A.A.; Utomo, R.G. An IoT-based Coastal
associated security issues, and the machine learning solutions
Recreational Suitability System using Effective
that can mitigate these problems. Securing IoT devices and
Messaging Protocol. Int. J. Adv. Comput. Sci. Appl. 2021,
systems requires a comprehensive analysis of IoT system
12, 8.
architectures and the various cyberattacks that can compromise
them layer by layer. In this study, we explored how different [14] Routray, S.K.; Gopal, D.; Javali, A.; Sahoo, A.
machine learning and deep learning technologies can be Narrowband IoT (NBIoT) Assisted Smart Grids. In
leveraged to enhance IoT security. For IoT security to be truly Proceedings of the 2021 International Conference on
effective, it must be underpinned by machine learning or deep Artificial Intelligence and Smart Systems (ICAIS),
learning models that are driven by relevant data attributes. Coimbatore, India, 25–27March 2021; pp. 1454–1458.
[15] Sangra, P.; Rana, B.; Singh, Y. Energy efficiency in IoT-
9. REFERENCES based smart healthcare. In Proceedings of Third
[1] Q. Zhou and J. Zhang, "Research prospect of Internet of International Conference on Computing,
Things geography", Proceedings of the 19th International Communications, and Cyber-Security; Springer:
Conference on Geoinformatics, pp. 1-5, 2011. Singapore, 2023; pp. 503–515.
53
International Journal of Computer Applications (0975 – 8887)
Volume 186 – No.45, October 2024
[16] Alshamrani, M. IoT and artificial intelligence [30] Rasheed, M.A.; Saleem, J.; Murtaza, H.; Tanweer, H.A.;
implementations for remote healthcare monitoring Rasheed, M.A.; Ahmed, M. A Survey on Fog computing
systems: A survey. J. King Saud Univ. Comput. Inf. Sci. in IoT. VFAST Trans. Softw. Eng. 2022, 9, 4.
2021, 34, 4687–4701. [31] Yassein, M.B.; Shatnawi, M.Q. Application layer
[17] S. Bharati, M. R. H. Mondal and P. Podder, "A Review on protocols for the Internet of Things: A survey. In
Explainable Artificial Intelligence for Healthcare: Why, Proceedings of the 2016 International Conference on
How, and When?," in IEEE Transactions on Artificial Engineering & MIS (ICEMIS), Agadir, Morocco, 22–24
Intelligence, vol. 5, no. 4, pp. 1429-1442, April 2024, doi: September 2016; pp. 1–4.
10.1109/TAI.2023.3266418. [32] Donta, P.K.; Srirama, S.N.; Amgoth, T.; Annavarapu,
[18] Bharati, S., Mondal, M. R. H., Podder, P., & Kose, U. C.S.R. Survey on recent advances in IoT application layer
(2023). Explainable artificial intelligence (XAI) with protocols and machine learning scope for research
IoHT for smart healthcare: A review. Interpretable directions. Digit. Commun. Netw. 2021, 8, 727–744.
Cognitive Internet of Things for Healthcare, 1-24. [33] Kakkar, L.; Gupta, D.; Saxena, S.; Tanwar, S. IoT
[19] Bharati, S., & Podder, P. (2022). Machine and deep architectures and its security: A review. In Proceedings of
learning for iot security and privacy: applications, the Second International Conference on Information
challenges, and future directions. Security and Management and Machine Intelligence; Springer:
communication networks, 2022(1), 8951961. Singapore, 2021; pp. 87–94.
[34] Noura, M.; Atiquzzaman, M.; Gaedke, M. Interoperability
[20] Khandoker Hoque, Md Boktiar Hossain, Denesh Das, in Internet of Things: Taxonomies and Open Challenges.
Partha Protim Roy . Integration of IoT in Energy Sector. Mob. Netw. Appl. 2018, 24, 796–809
International Journal of Computer Applications. 186, 36 (
Aug 2024), 32-40. DOI=10.5120/ijca2024923981. [35] Nawalagatti, A. IoT: A Boon for Advancement of
Technology. Int. J. Res. Appl. Sci. Eng. Technol. 2022,
[21] Sarker, B., Sharif, N. B., Rahman, M. A., & Parvez, A. S. 10, 652–655
(2023). AI, IoMT and Blockchain in Healthcare. Journal
of Trends in Computer Science and Smart Technology, [36] Ja, S.; Dhasb, J.T.M.; Angelc, T.S. Proposed Novel
5(1), 30-50. Methodology for Automatic Drainage Block
Identification in Smart Cities Using Internet of Things. In
[22] Kaur, J.; Jaskaran; Sindhwani, N.; Anand, R.; Pandey, D. Advances in Parallel Computing Algorithms, Tools and
Implementation of IoT in Various Domains, in IoT Based Paradigms; IOS Press: Amsterdam, The Netherlands,
Smart Applications; Springer: Berlin/Heidelberg, 2022.
Germany, 2023; pp. 165–178.
[37] Cˇ olakovic´, A.; Salihovic´, N.; Dželihodžic´, A.
[23] Albalawi, A.M.; Almaiah, M.A. Assessing and reviewing Adaptive Traffic Management Systems Based on the
of cyber-security threats, attacks, mitigation techniques in Internet of Things (IoT). In Proceedings of Advanced
IoT environment. J. Theor. Appl. Inf. Technol. 2022, 100, Technologies, Systems, and Applications VII:
2988–3011. Proceedings of the International Symposium on
[24] Deep, S.; Zheng, X.; Jolfaei, A.; Yu, D.; Ostovari, P.; Innovative and Interdisciplinary Applications of
Bashir, A.K. A survey of security and privacy issues in the Advanced Technologies (IAT) 2022; Springer
Internet of Things from the layered context. Trans. Emerg. International Publishing: Cham, Switzerland, 2022; pp.
Telecommun. Technol. 2020, 33, e3935. 426–437.
[25] Navya, P.; Rama, G.S.; Kumar, T.P.; Pasha, S.N.; [38] Podder, P., Zawodniok, M., & Madria, S. (2024, June).
Mahender, K. IoT technology: Architecture, stack, Deep Learning for UAV Detection and Classification via
security risks, privacy risks and its applications. In Radio Frequency Signal Analysis. In 2024 25th IEEE
Proceedings of AIP Conference Proceedings; AIP International Conference on Mobile Data Management
Publishing LLC.: College Park, MD, USA, 2022; p. (MDM) (pp. 165-174). IEEE.
020062. [39] Al-lQubaydhi, Nader, et al. "Deep learning for unmanned
[26] Chatterjee, U.; Ray, S. Security Issues on IoT aerial vehicles detection: A review." Computer Science
Communication and Evolving Solutions. In Soft Review 51 (2024): 100614.
Computing in Interdisciplinary Sciences; Springer: [40] Amit Deb Nath, Rahmanul Hoque, Md. Masum Billah,
Berlin/Heidelberg, Germany, 2022; pp. 183–204. Numair Bin Sharif, Mahmudul Hoque . Distributed
[27] Haque, A.K.M.B.; Bhushan, B.; Dhiman, G. Parallel and Cloud Computing: A Review. International
Conceptualizing smart city applications: Requirements, Journal of Computer Applications. 186, 16 ( Apr 2024),
architecture, security issues, and emerging trends. Expert 25-32. DOI=10.5120/ijca2024923547
Syst. 2021, 39, e12753. [41] Abusitta, A., de Carvalho, G.H., Wahab, O.A., Halabi, T.,
[28] Jangjou, M.; Sohrabi, M.K. A Comprehensive Survey on Fung, B.C. and Al Mamoori, S., 2023. Deep learning-
Security Challenges in Different Network Layers in Cloud enabled anomaly detection for IoT systems. Internet of
Computing. Arch. Comput. Methods Eng. 2022, 29, Things, 21, p.100656.
3587–3608. [42] Mekala, S. H., Baig, Z., Anwar, A., & Zeadally, S. (2023).
[29] Zahran, S.; Elkadi, H.; Helm,W. Fog of Things Cybersecurity for Industrial IoT (IIoT): Threats,
Framework to Handle Data Streaming Heterogeneity on countermeasures, challenges and future directions.
Internet of Things. In Proceedings of International Computer Communications.
Conference on Advanced Intelligent Systems and [43] Huang, B., Chaki, D., Bouguettaya, A. and Lam, K.Y.,
Informatics; Springer International Publishing: Cham, 2023. A survey on conflict detection in iot-based smart
Switzerland, 2022; pp. 653–667. homes. ACM Computing Surveys, 56(5), pp.1-40.
54
International Journal of Computer Applications (0975 – 8887)
Volume 186 – No.45, October 2024
[44] Wang, X., Zhu, H., Ning, Z., Guo, L. and Zhang, Y., 2023. [54] Hoque, K., Hossain, M. B., Sami, A., Das, D., Kadir, A.,
Blockchain intelligence for internet of vehicles: & Rahman, M. A. (2024). Technological trends in 5G
Challenges and solutions. IEEE Communications Surveys networks for IoT-enabled smart healthcare: A review.
& Tutorials. International Journal of Science and Research Archive,
[45] E. Manavalan, K. Jayakrishna A review of internet of 12(2), 1399-1410.
things (iot) embedded sustainable supply chain for [55] Bharati, Subrato, et al. "Comparative performance
industry 4.0 requirements Comput. Ind. Eng., 127 (2019), analysis of different classification algorithm for the
pp. 925-953 purpose of prediction of lung cancer." Intelligent Systems
[46] Toorajipour, R., Sohrabpour, V., Nazarpour, A., Oghazi, Design and Applications: 18th International Conference
P. and Fischl, M., 2021. Artificial intelligence in supply on Intelligent Systems Design and Applications (ISDA
chain management: A systematic literature review. 2018) held in Vellore, India, December 6-8, 2018, Volume
Journal of Business Research, 122, pp.502-517. 2. Springer International Publishing, 2020.
[47] Elghamrawy, S.M.; Lotfy, M.O.; Elawady, Y.H. An [56] Javed Mehedi Shamrat, F. M., Tasnim, Z., Chowdhury, T.
Intrusion Detection Model Based on Deep Learning and R., Shema, R., Uddin, M. S., & Sultana, Z. (2022).
Multi-Layer Perceptron in the Internet of Things (IoT) Multiple cascading algorithms to evaluate performance of
Network. In International Conference on Advanced face detection. In Pervasive Computing and Social
Machine Learning Technologies and Applications; Networking: Proceedings of ICPCSN 2021 (pp. 89-102).
Springer: Berlin/Heidelberg, Germany, 2022; pp. 34–46. Springer Singapore.
[48] Uhricek, D.; Hynek, K.; Cejka, T.; Kolar, D. BOTA: [57] Javed Mehedi Shamrat, F. M., Ghosh, P., Tasnim, Z.,
Explainable IoT Malware Detection in Large Networks; Khan, A. A., Uddin, M. S., & Chowdhury, T. R. (2022).
IEEE: New York, NY, USA, 2022; p. 1. Human Face recognition using eigenface, SURF method.
In Pervasive Computing and Social Networking:
[49] Madhu, B.; Chari, M.V.G.; Vankdothu, R.; Silivery, A.K.; Proceedings of ICPCSN 2021 (pp. 73-88). Springer
Aerranagula, V. Intrusion detection models for IOT Singapore.
networks via deep learning approaches. Meas. Sens. 2022,
100641. [58] Kowsher, M., Tahabilder, A., Sanjid, M. Z. I., Prottasha,
N. J., Uddin, M. S., Hossain, M. A., & Jilani, M. A. K.
[50] Al-Shareeda, M.A.; Manickam, S.; Saare, M.A. DDoS (2021). LSTM-ANN & BiLSTM-ANN: Hybrid deep
attacks detection using machine learning and deep learning models for enhanced classification accuracy.
learning techniques: Analysis and comparison. Bull. Procedia Computer Science, 193, 131-140.
Electr. Eng. Inform. 2023, 12, 930–939.
[59] Hoque, R., Maniruzzaman, M., Michael, D. L., & Hoque,
[51] Gopal, S.B.; Poongodi, C.; Nanthiya, D.; Kirubakaran, T.; M. (2024). Empowering blockchain with SmartNIC:
Logeshwar, D.; Saravanan, B.K. Autoencoder based Enhancing performance, security, and scalability. World
Architecture for Mitigating Phishing URL attack in the Journal of Advanced Research and Reviews, 22(1), 151-
Internet of Things (IoT) Using Deep Neural Networks. In 162.
2022 6th International Conference on Devices, Circuits
and Systems (ICDCS); IEEE: New York, NY, USA, 2022; [60] Hoque, R., Billah, M., Debnath, A., Hossain, S. S., &
pp. 427–431. Sharif, N. B. (2024). Heart Disease Prediction using SVM.
International Journal of Science and Research Archive,
[52] Bhattacharya, S.; Ghorai, S.; Khan, A.K. Systematic 11(2), 412-420.
Study of Detection Mechanism for Network Intrusion in
Cloud, Fog, and Internet of Things Using Deep Learning. [61] Mohanta, B. K., Jena, D., Satapathy, U., & Patnaik, S.
In Human-Centric Smart Computing; Springer: (2020). Survey on IoT security: Challenges and solution
Berlin/Heidelberg, Germany, 2023; pp. 31–43. using machine learning, artificial intelligence and
blockchain technology. Internet of Things, 11, 100227.
[53] Saheed, Y.K.; Baba, U.A.; Orje-Ishegh, T.; Longe, O.B.
An Efficient Machine Learning and Deep Belief Network [62] Chowdhury, I. K., & Yu, W. B. (2024). Information
Models for Wireless Intrusion Detection System. 2022. extraction from the reviews of AI applications using SAS
text Mining Process. Issues in Information Systems, 25(4),
127-135.
55
IJCATM : www.ijcaonline.org