Content uploaded by Usman Haider
Author content
All content in this area was uploaded by Usman Haider on Jan 27, 2024
Content may be subject to copyright.
1
AI-based Secure Wireless Communication Technologies & Cyber
Threats for IoT-Networks
Usman Haider1, Bakhtawar Nawaal2, Inam Ullah Khan3, and Salma El Hajjami4
1National University of Computer and Emerging Sciences Islamabad, Pakistan. (Email:
usmanhaider@ieee.org)
2University of Engineering and Technology Taxila, Pakistan. (Email: bakhtawarnawaal@gmail.com)
3Isra University Islamabad Campus, Pakistan. (Email: inamullahkhan05@gmail.com)
4LABSIV Laboratory, Ibnou Zohr University Agadir, Morocco. (Email: s.elhajjami@uiz.ac.ma)
DOI: 10.1201/9781003404361-4
ABSTRACT
Artificial intelligence (AI) proved to be the fate-changer for this world. It has created a huge space to
progress in this world. All integrated technologies are moving towards automation and smart
transformation using artificial intelligence. AI technologies are having many applications in
autonomous vehicles, ad-hoc networking, cybersecurity solutions, healthcare and agriculture. On
parallel, the trend of wireless communication is main topic of study to get rid of corded networks
along with the mitigation of latency from network. Today, no communication can be completed
without the use of wireless technologies. In this modern era, there exist many related applications
which make use of next generation artificial intelligence. Smart communication can be made possible
using artificial intelligence. This work presents a survey related to AI-based applications, IDS, cyber-
attacks on IoT-network and AI tools are briefly discussed. Also, secure communication like network
traffic monitoring is incorporated in the research study.
Keywords
AI, Smart Computing; IoT, Wireless Communication, IDS, ML.
1. INTRODUCTION
Artificial intelligence (AI) has opened countless opportunities to mankind and each of it contains a
world in itself. Researchers are trying to explore each one of them where humans can take benefit
from new emerging technologies. AI is having application in almost every segment of life. However,
autonomous vehicles are considered new application in this field of study [1]. Tesla is a renowned
company by introducing driver-less cars. Furtherly, AI enabled medicines are quite helpful in
pandemic. Therefore, due to artificial intelligence detection and diagnosis of many deadly diseases is
made possible. Various diseases are now being diagnosed by systems based on AI. Also,
cancerous/tumorous cells are easily monitored using AI models which use to decrease the fatality rate
[2], [3]. Moreover, AI has found many applications in cardiology, neurology and dermatology. For
the purpose of data & information security end-devices use to safeguard overall network form
intrusion. More interestingly, intrusion Detection System (IDS), Intrusion Prevention System (IPS)
powered by artificial intelligence can easily detect threats [4], [5]. All industries are on their way to
automation because AI has created a large room for progress [6]. While, AI tools are quite in demand,
thus easy to make decision on the right time. AI based systems comprised of wireless sensor nodes
2
which constantly monitor factors related to crops [7]. Figure 1 demonstrates use of artificial
intelligence in cyber security, autonomous vehicles, ad hoc networks, healthcare, agriculture and
voice assistants.
Figure 1: Uses of Artificial Intelligence (AI)
Wireless communication networks received attention from the day first. Now the world is about
to launch the 6th generation (6G) wireless network commercially. 6G is going to transform world into
newer place. While, automation is the need of modern world which dive AI enabled networks to
achieve various goals [8]. Wireless communication networks use the wireless channels for a variety of
communication [9], [10]. Advance networks are used in Television, Radio Broadcasting, Satellite
Communication, Radar, Mobile Telephone System (Cellular Communication), Global Positioning
System (GPS), Infrared Communication, WLAN (Wi-Fi) and Bluetooth. Recently, Wireless Sensor
Node (WSN) and Ad-hoc Communication Networks are trending topics where researchers are keenly
working on it. Wireless sensor networks (WSN) are using IoT-devices which cost effective [11].
However, ad hoc networks use wireless communication technologies for better signal strength.
Therefore, there are different types of ad hoc networks which include MANET, FANET, RANET and
VANET [12]. Due to artificial intelligence wireless technologies are improved with the passage of
time. While, AI-powered wireless communication systems are in demand.
As mentioned earlier the latest proposition for wireless communication is 6G. Transfer learning
(TL) is a novel approach for 6G networks which incites new domains to learn from previous events
and apply on wireless communication fields [13]. 6G enabled quantum computing will remove error
and will provide solutions to existing problems [14]. There are many issues been encountered, where
most critical one is performance of both Machine Learning (ML) algorithms and Wireless Networks
[15]. More interestingly, high accuracy in machine learning classifiers needs to be balanced.
However, in machine learning high accuracy, false alarm, precision, recall, support and F1 score need
to be properly improved for achieving high standards of automation.
The deficiencies discussed later need to be addressed by researchers which will be significant
contribution. In addition, especially for artificial intelligence governments are planning to make better
3
laws for machine. Furtherly, as machine industry is growing day by day therefore, AI with ethics will
play important role in smart world [16], [17], [18].
2. Literature Study
This section provides brief literature study regarding AI enabled wireless communication techniques
which are as follow:
Meta-heuristic search technique is basically sub-part of artificial intelligence. Therefore, ant
colony optimization protocol using wireless communication networks are deployed in flying ad hoc
networks. While, comparative analysis is performed to check the performance of AntHocNet with
other traditional routing protocols. Moreover, end-to-end delay is the major problem found during
communication [19]. Accordingly, Inam Ullah Khan et al, proposed a novel routing protocol called E-
AntHocNet which is used to improve energy efficiency within UAV-network. Random way point
(RWP) model is used to check the behavior of unmanned aerial vehicles [20]. Existing mobility
models of MANETs are used in UAV-network therefore hybrid models need to be designed. IoT-
networks are having many issues especially signal strength from base station to IoT-nodes. Due to
that machine learning classifiers improve communication standards within nodes. While, internet of
flying vehicles uses to have limited mobility due to wireless connectivity [21].
Although, 3D modeling improve signal strength measurement in IoT connected networks. Both
scenarios of indoor and outdoor are used for node localization. Where, for location tracking of IoT-
nodes localization is quite helpful. Similar, work need to be demonstrated in real-time environment to
improve received signal strength indicator [22]. IoT enabled UAVs are having application real-time
modeling in health and sports. Therefore, routing protocols plays important role during overall
communication within nodes [23]. Seema Begum et al, introduced a new approach which is based on
cognitive modeling for IoT-networks. Furtherly, security need to be ensured for IoT-networks. Due to
that markov chain enabled IDS is designed to detect DoS, DDoS and ping of death attacks [24], [25].
Sajid, Faiqa, et al. [26] proposed IoT based methodology for the classification of heart rate data for
the prevention of heart attack using machine learning technique through generated dataset secured by
RSA encryption. However, the data rates are slow due to RSA because it involves large number.
Khan, Inam Ullah, et al. [27] explained dynamic behavior of UAVs, proposed an Unmanned
aerial-AntHocNet protocol and compared it with other modern routing protocols using Random Way
Mobility Model and achieved good results. As only one mobility model is being used in
experimentation so the results on other model can be undefined and the communication standard can
be compromised. Khan, Inam Ullah, et al. [28] proposed Improved Sequencing Heuristic DSDV
(ISH-DSDV) protocol to address the energy problems in arial vehicles. Table 1 depicts various
artificial intelligence approaches with limitations.
Table 1: Different AI based approaches in Wireless Communication with limitations
Reference
Technique
Used
Description
Limitations
[29]
DNN
This work used DNNs to for
various wireless communication
processes i.e., channel modeling,
channel encoding/decoding signal
detection etc.
These use of DNN in wireless
communication make it
vulnerable to various kind of
attacks.
4
[30]
KNN, SVM
algorithms
This paper proposed multiclass
classification for the selection of
antenna using machine learning.
In KNN, it is very difficult to
designate the correct value of
K and somehow it is
computationally not enough
efficient.
[31]
Federated
Learning (FL)
This work proposed Collaborative
Federated Learning (CFL) that is
based on distributed ML, for
optimized performance.
In FL, there the use of
unsupervised algorithms is
preferred and some limitations
come across during data
cleaning and labeling.
[32]
DNN
This paper proposed the used of
deep learning for optical wireless
communication to counter various
design challenges.
The system training using is
very slow.
[33]
CNNs, FNNs,
RF & GRUs
This work tried to address the
channel assignment problems in
wireless communication using ML
algorithms & convex optimization-
based algorithms.
The system is not well efficient
in case of larger number of
users and sub-channels
[34]
DNN
This work proposed Deep Neural
Networks for IDS using cross-
correlation process and compared
performance with some other ML
algorithms.
The accuracy of the system
significantly low much better
system available.
[35]
ANN
The paper proposed the use of ML
for extremely low latency for next-
generations of wireless
communication.
The application of ANNs is
significantly time consuming
and computationally
expensive.
[36]
DT
This work described the benefits of
ML in wireless communication in
relay selection through multiclass
classification.
The implementation of DT is
quite expensive involving
repetitive training as well as
having higher complexity.
[37]
Distributed
Batch Gradient
Descent
(DBGD)
This research proposed novel
approach for D2D communication
with better accuracy and reduced
training delay.
Gradient Descent (GD)
occupies some matematical
limitations.
[38]
RF, AB, GBM,
XGB & ETC
This work presented an assessment
study of seven ML algorithms for
an efficient anomaly-based IDS
using three datasets for learning
also evaluated the performance
through Raspberry-Pi.
Anomaly-based IDS has
usually significantly high false
alarm rate.
5
3. AI FOR NEXT GENERATION WIRELESS NETWORKS
The wireless communication can be made possible from sender to receiver using medium. In
first generation of wireless communication, analogue communication was utilized as backbone which
was later changed to digital in second generation (2G) with the evolution of GSM. However, 3G
technology is having working scenario of circuit switching through UMTS using different techniques
of CDMA. While, 4G communication networks is based on circuit switching and packet switching.
More interestingly, 5G is mainly working on packet switching [39], [40], [41]. 6G communications
has improved channels in next generation intelligent networks. In comparison with 5G networks, 6G
is much more advanced [42]. Some researchers called AI as a “Double Edged Sword” in 6th
Generation of Wireless Communication because threat resistance and end-to-end automation in the
network [43]. AI is serving as a base in 6G for many modern technologies like Smart Computing,
Augmented Reality, Extended Reality (XR) etc. [44]. For short distances, the Optical Wireless (OW)
communication is an excellent approach with a speed of gigabytes per second. Moreover, the different
techniques of deep learning (DL) are being used to deal with many parametrical complications [45],
[46]. Figure 2 displays a sketch of Modern AI based Wireless Communication System.
Figure 2: AI-Based Wireless Communication
4. APPLICATIONS OF AI FOR SMART COMPUTING
The definition of Smart computing is hidden in itself as S.M.A.R.T. It stands for Self-Monitoring,
Analysis, and Reporting Technology. It is used to monitor and detect any hardware failure in a system
automatically and first used for the following application with hard drives. Smart Computing emerged
to be an intelligent technology due to integration of AI. AI powered the smart computing and it found
6
many applications. In smart computing AI is used in Smart houses, Smart Grid, Smart Agriculture,
Smart Healthcare, Smart Cybersecurity, Smart Networking, smart vehicles etc.
4.1. SMART HOUSE
Smart house is building block of smart cities. Smart houses consist of intelligent appliances like smart
air conditioner, smart TV, smart refrigerator, smart lights, fans etc. A smart house enables you to
monitor the house 24 hours a day and to control all gadgets remotely [47]. You can have a check on
home security and you can turn on the AC or a heater before coming to home on a hot or cold day
respectively. Thus, smart computing makes your house secure and comfortable.
4.2. SMART GRID
A smart grid is a digital electricity network used to distribute electricity through two-way digital
communication. It has various advantages over a conventional grid system as it is more efficient,
transparent, reliable and it reduces consumption as well as cost of electricity [48]. It is also
environment friendly and much flexible in applications. Smart grid is composed of three types of
systems; (i) Smart infrastructure system, (ii) Smart management system, (iii) Smart protection system
[49].
4.3. SMART NETWORKING & SECURITY
AI has also opened doors for intelligent networking. Device on each end learns the path that would be
feasible for the communication depending upon the applied protocol. Cybersecurity has been main
focus in AI and various novel techniques have been introduced in the security of networks. Intrusion
Detection System (IDS) and Intrusion Prevention System (IPS) have been powered with AI. They are
trained properly using appropriate ML algorithm for the possible kind of attack, also made intelligent
enough to detect zero-day exploit and programmed to take action automatically in case of intrusion
[50], [51]. In Signature-based IDS, the attack signature is already saved and possible threats are
matched and in Anomaly-based IDS the system is trained to sense attack in real environment using
the knowledge of training dataset [52], [53].
4.4. SMART HEALTHCARE
Healthcare has been extremely grown with the integration of artificial intelligence and internet of
things (IoT). The increasing number of chronic diseases made researcher use the latest technologies in
health care for diagnosis and treatment to control patient’s critical condition from getting worse.
Patient can be anywhere under supervision through various devices accessed through doctor’s
workstation and AI has made the machines intelligent enough to alarm any emergency depending on
parameters under supervision through various sensors. In Smart healthcare, a patient’s ill organ is
tested for every kind of threat automatically with optimal diagnosis that might have skipped by
doctor’s examination [54], [55].
4.5. SMART AGRICULTURE
Agriculture has been smart since the use of AI and IoT. Wireless Sensor Nodes (WSNs) have found
huge application in smart agriculture. The Network of WSNs is energized with AI over intelligent
decisions depending upon the circumstances. AI has provided the farmers the pest control on the very
early stage to prevent damage to crops. The irrigation system can not only be controlled remotely but
7
also automated via sensor readings. Even robots can be used to sow seeds and reap crops. Thus, AI in
smart agriculture gives you the efficient management of all the agricultural resources [56], [57].
5. AI FOR CYBER SCIENCE
Some of the famous attacks are Denial of Service (DOS), Distributed Denial of Service (DDOS),
Phishing Attack, Ping of Death, Ransomwares, Man-in-the-Middle Attack, SQL Injection, Malware
etc. In past some very huge cyberattacks occurred that directly affect privacy, stake and finances of
public as well as companies [58]. Previously, only malwares could be detected because the developer
had their identity and could be easily through signature detection but it leaves behind the unknown
threats that way to evolution of anomaly detection [59]. AI-based solutions have really boomed the
security industry with a variety of efficient solution. Some works proposed the use of AI in intelligent
detection and prevention through Artificial Police Agents in a decentralized fashion creating an
artificial immune system like a human body [60]. While, some researchers using ML-based IDS, IPS,
firewalls etc. for efficient network security even against Zero-Day Exploit. AI also proposes the
Cloud-based security solutions [61], [62]. Thus, with the introduction of AI in cyber science, the
critical infrastructure is more secure than with old security solutions.
6. CYBER THREATS
There are numerous cyber threats in today’s era each of them has multiple types. Some of the famous
cyber-attacks are discussed below:
6.1. DENIAL OF SERVICE (DOS) ATTACK
It is most famous, common and a deadly attack. In this attack, attacker has the only intension to keep
the target down from its services and even the legal users are unable to connect the server. A huge
amount of traffic is sent by the attacker to the victim that is unable to handle that then turn the server
down completely [63].
Figure 3: Denial of Service Attack (DoS)
6.2. DISTRIBUTED DENIAL OF SERVICE (DDOS) ATTACK
DDoS is a type of DoS or it can be called an advanced and more destructive version of DoS. The
intension of attacker is same as later but with different approach. The attacker uses various
compromised PCs/systems to ping the victim through various parts of world thus generating a huge
amount of traffic and dismantling the up state of victim [64].
6.3. DOMAIN NAME SYSTEM (DNS) ATTACK
DNS attack targets the DNS service of the network thus compromising its sustainability and
availability. It can slow down the web server thus affecting its ranking. It redirects the network traffic
8
to a malicious website instead of the legitimate website by changing the IP address in DNS server
thus corrupting it. DNS attack is usually done through cache poisoning [65]. A DNS attack is shown
in figure 4.
Figure 4: Domain Name System Attack
6.4. SYBIL ATTACK
The intruder using the sybil tries to own the network through various active false identities by a single
node. It is a serious threat to peer-to-peer network especially because the hacker is pretending to be
many persons at the same time and can fully control the network. Usually, sybil attacks are been
carried on the Tor Network. According to studies, there are 51% attacks of this category in the
blockchain networks [66]. This fake reviews and comments on ecommerce websites like Amazon are
an example of sybil attacks. Figure 5 shows the sketch of a sybil attack.
Figure 5: Sketch of Sybil Attack
6.5. PING OF DEATH (POD) ATTACK
In this kind of attack, the attacker tries to freeze and destabilize the victim through sending
malfunctioned or oversized packets. The attacker uses the hit and trail method to get to know about
9
system’s limit, through continuous sending packets. As the attacker reaches beyond system limits, the
system is unable to process beyond functional packet-sized system stops to respond. Some researchers
call PoD a kind of DoS and DDoS attack [67]. Figure 6 describes the idea of PoD attack.
Figure 6: Ping of Death Attack
7. FUTURE DIRECTIONS
In near future everything is going to be smart where security is a serious problem. This critical
problem is addressed by artificial intelligence, machine learning, big data, evolutionary computing,
ant colony optimization, genetic algorithm etc. Thus, the researchers working on smart gadgets and
IoTs should also work on their security and threat resistance as well. Moreover, security solutions
with more accurate results are needed [68], [69], [70].
8. CONCLUSION
The technology is going to surpass 24 hours supervision in very near future and artificial intelligence
is the key to new transformation. However, applications of AI are countless because an intelligent
system can be deployed anywhere which can efficiently perform assigned task if trained properly.
Now a day’s, every person is having a wireless device in his/her pocket and is connected with the
huge communication system of smart world. Wireless systems include base stations for local as well
as national level communication and satellites on the national as well as on international level. AI in
collaboration with wireless communication is going to change world dynamics and giving rise to
smart computing. In short, the future is very bright on this planet through practices of AI on
intelligent systems thus forming an entirely smart world.
REFERENCES
[1] Abdul jabbar, Rusul, et al. "Applications of artificial intelligence in transport: An overview."
Sustainability 11.1 (2019): 189.
[2] Nichols, James A., Hsien W. Herbert Chan, and Matthew AB Baker. "Machine learning:
applications of artificial intelligence to imaging and diagnosis." Biophysical reviews 11.1
(2019): 111-118.
10
[3] Subhan, Fazal, et al. "Cancerous Tumor Controlled Treatment Using Search Heuristic (GA)-
Based Sliding Mode and Synergetic Controller." Cancers 14.17 (2022): 4191.
[4] Kumar, Gulshan, and Krishan Kumar. "The use of artificial-intelligence-based ensembles for
intrusion detection: a review." Applied Computational Intelligence and Soft Computing 2012
(2012).
[5] Yildirim, Merve. "Artificial intelligence-based solutions for cyber security problems." Artificial
Intelligence Paradigms for Smart Cyber-Physical Systems. IGI Global, 2021. 68-86.
[6] Battina, Dhaya Sindhu. "Application Research of Artificial Intelligence in Electrical
Automation Control." International Journal of Creative Research Thoughts (IJCRT),
ISSN (2015): 2320-2882.
[7] Eli-Chukwu, Ngozi Clara. "Applications of artificial intelligence in agriculture: A
review." Engineering, Technology & Applied Science Research 9.4 (2019): 4377-4383.
[8] You, Xiaohu, et al. "Towards 6G wireless communication networks: Vision, enabling
technologies, and new paradigm shifts." Science China Information Sciences 64.1 (2021): 1-74.
[9] Stallings, William. Wireless communications & networks. Pearson Education India, 2009.
[10] Li, Xichun, et al. "The future of mobile wireless communication networks." 2009 International
Conference on Communication Software and Networks. IEEE, 2009.
[11] García-Hernández, Carlos F., et al. "Wireless sensor networks and applications: a survey."
IJCSNS International Journal of Computer Science and Network Security 7.3 (2007): 264-273.
[12] Xu, Bangnan, Sven Hischke, and Bernhard Walke. "The role of ad hoc networking in future
wireless communications." International Conference on Communication Technology
Proceedings, 2003. ICCT 2003.. Vol. 2. IEEE, 2003.
[13] Wang, Meiyu, et al. "Transfer learning promotes 6G wireless communications: Recent advances
and future challenges." IEEE Transactions on Reliability 70.2 (2021): 790-807.
[14] Akyildiz, Ian F., Ahan Kak, and Shuai Nie. "6G and beyond: The future of wireless
communications systems." IEEE access 8 (2020): 133995-134030.
[15] Groumpos, Peter P. "Artificial intelligence: Issues, challenges, opportunities and threats."
Conference on Creativity in Intelligent Technologies and Data Science. Springer, Cham, 2019.
[16] Ghallab, Malik. "Responsible AI: requirements and challenges." AI Perspectives 1.1 (2019): 1-
7.
[17] Rodrigues, Rowena. "Legal and human rights issues of AI: Gaps, challenges and
vulnerabilities." Journal of Responsible Technology 4 (2020): 100005.
[18] Borenstein, Jason, and Ayanna Howard. "Emerging challenges in AI and the need for AI ethics
education." AI and Ethics 1.1 (2021): 61-65.
[19] Khan, Inam Ullah, et al. "Reinforce based optimization in wireless communication technologies
and routing techniques using internet of flying vehicles." The 4th international conference on
future networks and distributed systems (ICFNDS). 2020.
[20] Khan, Inam Ullah, et al. "Smart IoT control-based nature inspired energy efficient routing
protocol for flying ad hoc network (FANET)." IEEE Access 8 (2020): 56371-56378.
[21] Khan, Inam Ullah, et al. "Routing protocols & unmanned aerial vehicles autonomous
localization in flying networks." International Journal of Communication Systems (2021):
e4885.
[22] Khan, Inam Ullah, et al. "RSSI-controlled long-range communication in secured IoT-enabled
unmanned aerial vehicles." Mobile information systems 2021 (2021).
[23] Khan, Inam Ullah, et al. "Monitoring system-based flying IoT in public health and sports using
ant-enabled energy-aware routing." Journal of Healthcare Engineering 2021 (2021).
11
[24] Khan, Inam Ullah, et al. "Intelligent Detection System Enabled Attack Probability Using
Markov Chain in Aerial Networks." Wireless Communications and Mobile Computing 2021
(2021).
[25] Begum, Seema, et al. "Source routing for distributed big data-based cognitive internet of things
(CIoT)." Wireless Communications and Mobile Computing 2021 (2021).
[26] Sajid, Faiqa, et al. "Secure and Efficient Data Storage Operations by Using Intelligent
Classification Technique and RSA Algorithm in IoT-Based Cloud Computing." Scientific
Programming 2022 (2022).
[27] Khan, Inam Ullah, et al. "A Novel Design of FANET Routing Protocol Aided 5G
Communication Using IoT." Journal of Mobile Multimedia (2022): 1333-1354.
[28] Khan, Inam Ullah, et al. "Improved sequencing heuristic DSDV protocol using nomadic
mobility model for FANETS." Comput., Mater. Continua 70.2 (2022): 3653-3666.
[29] Wang, Jun, et al. "Artificial intelligence and wireless communications." Frontiers of
Information Technology & Electronic Engineering 21.10 (2020): 1413-1425.
[30] Joung, Jingon. "Machine learning-based antenna selection in wireless communications." IEEE
Communications Letters 20.11 (2016): 2241-2244.
[31] Chen, Mingzhe, et al. "Wireless communications for collaborative federated learning." IEEE
Communications Magazine 58.12 (2020): 48-54.
[32] Lee, Hoon, et al. "Deep learning framework for wireless systems: Applications to optical
wireless communications." IEEE Communications Magazine 57.3 (2019): 35-41.
[33] Jia, Guangyu, et al. "Channel assignment in uplink wireless communication using machine
learning approach." IEEE Communications Letters 24.4 (2020): 787-791.
[34] Gowdhaman, V., and R. Dhanapal. "An intrusion detection system for wireless sensor networks
using deep neural network." Soft Computing 26.23 (2022): 13059-13067.
[35] Chen, Mingzhe, et al. "Artificial neural networks-based machine learning for wireless networks:
A tutorial." IEEE Communications Surveys & Tutorials 21.4 (2019): 3039-3071.
[36] Jagannath, Anu, Jithin Jagannath, and Tommaso Melodia. "Redefining Wireless
Communication for 6G: Signal Processing Meets Deep Learning with Deep Unfolding." arXiv
preprint arXiv:2004.10715 (2020).
[37] Cai, Xiaoran, et al. "D2D-enabled data sharing for distributed machine learning at wireless
network edge." IEEE Wireless Communications Letters 9.9 (2020): 1457-1461.
[38] Verma, Abhishek, and Virender Ranga. "Machine learning based intrusion detection systems
for IoT applications." Wireless Personal Communications 111.4 (2020): 2287-2310.
[39] Sharma, Pankaj. "Evolution of mobile wireless communication networks-1G to 5G as well as
future prospective of next generation communication network." International Journal of
Computer Science and Mobile Computing 2.8 (2013): 47-53.
[40] Vora, Lopa J. "Evolution of mobile generation technology: 1G to 5G and review of upcoming
wireless technology 5G." International journal of modern trends in engineering and research
2.10 (2015): 281-290.
[41] Gawas, Anju Uttam. "An overview on evolution of mobile wireless communication networks:
1G-6G." International Journal on Recent and Innovation Trends in Computing and
Communication 3.5 (2015): 3130-3133.
[42] Yang, Ping, et al. "6G wireless communications: Vision and potential techniques." IEEE
network 33.4 (2019): 70-75.
[43] Siriwardhana, Yushan, et al. "AI and 6G security: Opportunities and challenges." 2021 Joint
European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit).
IEEE, 2021.
12
[44] Ahammed, Tareq Bin, and Ripon Patgiri. "6G and AI: The emergence of future forefront
technology." 2020 Advanced Communication Technologies and Signal Processing (ACTS).
IEEE, 2020.
[45] Borah, Deva K., et al. "A review of communication-oriented optical wireless systems."
EURASIP Journal on Wireless Communications and Networking 2012 (2012): 1-28.
[46] Lee, Hoon, et al. "Deep learning framework for wireless systems: Applications to optical
wireless communications." IEEE Communications Magazine 57.3 (2019): 35-41.
[47] Lytvyn, Vasyl, et al. "Intelligent system of a smart house." 2019 3rd International Conference
on Advanced Information and Communications Technologies (AICT). IEEE, 2019.
[48] Moslehi, Khosrow, and Ranjit Kumar. "A reliability perspective of the smart grid." IEEE
transactions on smart grid 1.1 (2010): 57-64.
[49] Fang, Xi, et al. "Smart grid—The new and improved power grid: A survey." IEEE
communications surveys & tutorials 14.4 (2011): 944-980.
[50] Al-Omari, Mohammad, et al. "An intelligent tree-based intrusion detection model for cyber
security." Journal of Network and Systems Management 29 (2021): 1-18.
[51] Azeez, Nureni Ayofe, et al. "Intrusion detection and prevention systems: an updated review."
Data Management, Analytics and Innovation: Proceedings of ICDMAI 2019, Volume 1 (2020):
685-696.
[52] Kruegel, Christopher, and Thomas Toth. "Using decision trees to improve signature-based
intrusion detection." Recent Advances in Intrusion Detection: 6th International Symposium,
RAID 2003, Pittsburgh, PA, USA, September 8-10, 2003. Proceedings 6. Springer Berlin
Heidelberg, 2003.
[53] Jyothsna, V. V. R. P. V., Rama Prasad, and K. Munivara Prasad. "A review of anomaly based
intrusion detection systems." International Journal of Computer Applications 28.7 (2011): 26-
35.
[54] Alshehri, Fatima, and Ghulam Muhammad. "A comprehensive survey of the Internet of Things
(IoT) and AI-based smart healthcare." IEEE Access 9 (2020): 3660-3678.
[55] Chen, Xieling, et al. "Information fusion and artificial intelligence for smart healthcare: a
bibliometric study." Information Processing & Management 60.1 (2023): 103113.
[56] Ragavi, B., et al. "Smart agriculture with AI sensor by using Agrobot." 2020 Fourth
International Conference on Computing Methodologies and Communication (ICCMC). IEEE,
2020.
[57] Qazi, Sameer, Bilal A. Khawaja, and Qazi U. Farooq. "IoT-equipped and AI-enabled next
generation smart agriculture: a critical review, current challenges and future trends." IEEE
Access (2022).
[58] Choo, Kim-Kwang Raymond. "The cyber threat landscape: Challenges and future research
directions." Computers & security 30.8 (2011): 719-731.
[59] Stevens, Tim. "Knowledge in the grey zone: AI and cybersecurity." Digital War 1 (2020): 164-
170.
[60] Wirkuttis, Nadine, and Hadas Klein. "Artificial intelligence in cybersecurity." Cyber,
Intelligence, and Security 1.1 (2017): 103-119.
[61] Repalle, Syam Akhil, and Venkata Ratnam Kolluru. "Intrusion detection system using ai and
machine learning algorithm." International Research Journal of Engineering and Technology
(IRJET) 4.12 (2017): 1709-1715.
[62] Modi, Chirag, et al. "A survey of intrusion detection techniques in cloud." Journal of network
and computer applications 36.1 (2013): 42-57.
[63] Chao-Yang, Zhang. "DOS attack analysis and study of new measures to prevent." 2011
International Conference on Intelligence Science and Information Engineering. IEEE, 2011.
13
[64] Douligeris, Christos, and Aikaterini Mitrokotsa. "DDoS attacks and defense mechanisms:
classification and state-of-the-art." Computer networks 44.5 (2004): 643-666.
[65] Bassil, Ramzi, et al. "Security analysis and solution for thwarting cache poisoning attacks in the
domain name system." 2012 19th International Conference on Telecommunications (ICT).
IEEE, 2012.
[66] Levine, Brian Neil, Clay Shields, and N. Boris Margolin. "A survey of solutions to the sybil
attack." University of Massachusetts Amherst, Amherst, MA 7 (2006): 224.
[67] Yihunie, Fekadu, Eman Abdelfattah, and Ammar Odeh. "Analysis of ping of death DoS and
DDoS attacks." 2018 IEEE Long Island Systems, Applications and Technology Conference
(LISAT). IEEE, 2018.
[68] Kusyk, Janusz, M. Umit Uyar, and Cem Safak Sahin. "Survey on evolutionary computation
methods for cybersecurity of mobile ad hoc networks." Evolutionary Intelligence 10 (2018): 95-
117.
[69] Thakkar, Ankit, and Ritika Lohiya. "Role of swarm and evolutionary algorithms for intrusion
detection system: A survey." Swarm and evolutionary computation 53 (2020): 100631.
[70] Li, Jian-hua. "Cyber security meets artificial intelligence: a survey." Frontiers of Information
Technology & Electronic Engineering 19.12 (2018): 1462-1474.
