Conference PaperPDF Available

Abstract and Figures

Although the fifth generation wireless networks are yet to be fully investigated, the vision and key elements of the 6th generation (6G) ecosystem have already come into discussion. In order to contribute to these efforts and delineate the security and privacy aspects of 6G networks, we survey how security may impact the envisioned 6G wireless systems with the possible challenges and potential solutions. Especially, we discuss the security and privacy challenges that may emerge with the 6G requirements, novel network architecture, applications and enabling technologies including distributed ledger technologies, physical layer security, distributed artificial intelligence (AI)/ machine learning (ML), Visible Light Communication (VLC), THz bands, and quantum communication.
Content may be subject to copyright.
6G Security Challenges and Potential Solutions
Pawani Porambage, G¨
urkan G¨
ur, Diana Pamela Moya Osorio, Madhusanka Liyanage∗‡, Mika Ylianttila
Centre for Wireless Communications, University of Oulu, Finland
Zurich University of Applied Sciences (ZHAW) InIT, Switzerland
School of Computer Science, University College Dublin, Ireland
Email: [firstname.lastname],,
Abstract—Although the fifth generation wireless networks are
yet to be fully investigated, the vision and key elements of
the 6th generation (6G) ecosystem have already come into
discussion. In order to contribute to these efforts and delineate
the security and privacy aspects of 6G networks, we survey how
security may impact the envisioned 6G wireless systems with the
possible challenges and potential solutions. Especially, we discuss
the security and privacy challenges that may emerge with the
6G requirements, novel network architecture, applications and
enabling technologies including distributed ledger technologies,
physical layer security, distributed artificial intelligence (AI)/
machine learning (ML), Visible Light Communication (VLC),
THz bands, and quantum communication
Index Terms—6G, Security, Privacy, DLT, Quantum security,
AI/ML, Physical Layer Security, Security threats
Sixth generation (6G) of mobile communication is already
envisioned despite of the fact that 5G specifications are still de-
veloping and 5G coverage is not yet fully provided. The most
significant driving force in 6G leap is the inherent connected
intelligence in the telecommunication networks accompanied
with advanced networking and Artificial Intelligence (AI)
technologies [1]. However, the tight coupling between 6G and
AI does not by definition lead to better security and privacy.
It may also become a means or an apparatus to infringe
them in various cases. The evolution of security landscape of
telecommunication networks from 1G to 5G and then to the
envisioned 6G is illustrated in Figure 1. Moreover, there are
many efforts/proposals on blending novel technologies such
as blockchain, visible light communication (VLC), THz, and
quantum computing/communication features in 6G intelligent
networking paradigms in such a way to tackle the security and
privacy issues. Therefore, 6G security considerations need to
be analyzed in terms of physical layer security, network in-
formation security and advanced learning (e.g., deep learning)
related security [2].
Since the standard functions and specifications of 6G are
yet to be defined, there is still very limited literature that
clearly provides security and privacy insights of 6G networks.
In this article, we try to shed the light on how security may
impact the envisioned 6G wireless systems with a concise
discussion of challenges and then related potential solutions. In
particular, we survey the security and privacy challenges that
may arise with the expected 6G requirements, novel network
architecture, new applications and enabling technologies. We
also discuss the potential security solutions for 6G along the
directions of Distributed Ledger Technology (DLT), physical
layer security, quantum security, and distributed AI.
This section provides the possible security challenges and
threat landscape in future 6G wireless systems.
A. New 6G Requirements
Future 6G applications will pose stringent requirements
and require extended network capabilities compared to cur-
rently developed 5G networks [1]. These requirements are
summarized in Figure 2. They are established to enable the
wide range of key 6G use cases and thus can be categorized
accordingly. They also have major implications on how 6G
security is implemented. For Enhanced Ultra-Reliable, Low-
Latency Communication (ERLLC/eURLLC), the latency im-
pact of security workflows will be considered to ensure service
quality. Similarly, high reliability requirements call for very
efficient security solutions protecting availability of services
and resources. With Further enhanced Mobile Broadband
(FeMBB), extreme data rates will pose challenges regarding
traffic processing for security such as attack detection, AI/ML
pipelines, traffic analysis and pervasive encryption. That issue
can be alleviated with distributed security solutions since
traffic should be processed locally and on-the-fly in different
segments of the network, ranging from the edge to the core
service cloud. At this point, DLT will be instrumental with
transparency, security and redundancy attributes. Ultra massive
Machine Type Communication (umMTC) will serve critical
use-cases which impose much more stringent security require-
ments compared to 5G. In particular, Internet of Everything
(IoE) with very diverse capabilities will challenge the deploy-
ment and operation of security solutions such as distributed
AI/ML and privacy concerns. An important aspect is how to
integrate novel security enablers in an abundance of resource
constrained devices. Nevertheless, the security enforcement
will be more complex since network entities will be much
more mobile, changing their edge networks frequently and
getting services in different administrative domains.
B. New Architecture
1) Intelligence radio: State-of-the-art circuits, antennas,
meta-material-based structures, and the dramatic improvement
of AI chips have shed light on a paradigm-shift for hardware
Fig. 1: Evolution of communication network security landscape.
Latency 0.1 - 0.01 ms
Peak data rate > 1 Tbps
Mobility 1000 km/h
Area traffic capacity 1 Gb/m2
Intelligence Network
Edge Intelligence
Intelligence Radio
Industry 5.0
UAV based mobility
Connected Autonomous
Vehicles (CAV)
Smart Grid 2.0
Collaborative robots
Hyper-intelligent healthcare
Digital twin
Extended Reality
6G Architecture
6G Applications 6G Requirements
- AI
- Quantum communication
- THz bands
6G Technologies
New security requirements
New stakeholders
New attackers
Attacks on 6G architecture
(AI compromises, physical
attacks, physical layer
attacks, ...)
Attacks on key 6G
technologies (poisoning
attacks, eavesdropping, ...)
Fig. 2: 6G landscape and security composition.
architecture of 6G transceivers, where hardware can be sepa-
rated from the transceiver algorithms. Hence, the transceiver
algorithms could dynamically configure and update themselves
based on environment and hardware information. Intelligent
radio will involve cutting-edge AI/ML techniques in order
to address accurate channel modeling, agile physical layer
design, dynamic spectrum access, advanced network deploy-
ment, optimization, and autonomous orchestration issues in the
wireless domain [1]. Thus, suspicious activities by malicious
nodes need to be predicted during communication processes
for secure radios [3].
2) Edge Intelligence: When AI/ML algorithms are used to
acquire, storage or process data at the network edge, it is
referred to as edge intelligence (EI) [4]. In EI, an edge server
aggregates data generated by multiple devices associated with
it while sharing them with other edge servers for training
models, and later used for analysis and prediction, thus devices
can benefit from faster feedback, reduced latency and lower
costs while enhancing their operation. However, as data is
gathered from multiple sources, and the outcome of AI/ML
algorithms is highly data-dependent, EI is highly prone to
several security attacks. Attackers can exploit this dependency
to launch different attacks like data poisoning/evasion or
privacy violations, thus affecting the outputs of the AI/ML
applications and undermining the benefits of EI.
3) Intelligence Network Management: The extreme range
of 6G requirements and the envisioned full end-to-end (E2E)
automation of network and service management (i.e., use of
AI) demand a radical change in network service orchestration
and management in 6G architecture [5], [6]. ETSI ZSM (Zero-
touch network and Service Management) [7] architecture for
5G is a promising initiative to pave the path towards this
intelligence network management deployment.
Several security challenges have been identified in such
intelligence network management deployments. First, closed
loop network automation may introduce security threats such
as Denial of Service (DoS), deception and Man-In-The-
Middle (MITM) attacks [8]. DoS attacks can be performed by
gradually adding fake heavy load in virtual network functions
(VNFs) to increase the capacity of virtual machines (VMs).
MITM attacks can be performed by triggering fake fault events
and intercepting the domain control messages to reroute traffic
via malicious devices. Deception attacks can be performed
by tampering the transmitted data. Secondly, if 6G networks
use Intent-Based Interfaces similar to ZSM which can be
vulnerable for information exposure, undesirable configura-
tion and abnormal behavior attacks can occur. Intercepting
information of intents by unauthorized entities can also harm
system security objectives (e.g., privacy, confidentiality) and
lead to further subsequent attacks. Undesirable configuration
in Intent-Based Interfaces such as changing the mapping from
intent to action or decreasing the security level can jeopardize
the security of the whole management system. A malformed
intent could also have similar effects.
C. New Applications
6G will be the key communication infrastructure to sat-
isfy the demands of future needs of hyper-connected human
society by 2030 and beyond. It is foreseen that 6G paves
the way to the development of many new technologies such
as smart surfaces, zero-energy IoT devices, advanced AI
techniques, possible quantum computing systems, AI-powered
automated devices, AI-driven air interfaces, humanoid robots,
and self-sustained networks [1]. Moreover, the future trends
of digital societies such as massive availability of small data,
increasing elderly population, convergence of communica-
tion, sensing, and computing, gadget-free communication will
also demand new applications. The key 6G applications are
identified as UAV based mobility, Connected Autonomous
Vehicles (CAV), Smart Grid 2.0, Collaborative Robots, Hyper-
Intelligent Healthcare, Industry 5.0, Digital Twin and Extended
Reality [9]. The given applications may accommodate differ-
ent stakeholders and demand different levels of 6G security
requirements. Due to the novelty of these application domains
and the powerful attackers, the security requirements and the
challenges may hugely vary in 6G rather than in 5G (Table I).
D. Privacy
Privacy protection is a basic performance requirement and a
key feature in wireless communications in the envisioned era
of 6G [3], [10], which poses three key challenges:
The extremely large number of small chunks of data
exchanges in 6G may impose a greater threat on peoples’
privacy with an extensive attention attracted by govern-
mental and other business entities. The easier the data
is accessible and collectable in 6G era, the greater risk
they may impose on protecting user privacy and causing
regulatory difficulties.
When the intelligence is moving to the edge of the
network, more sophisticated applications will run on
mobile devices increasing the threats of attacks. However,
incorporating privacy protecting mechanisms in resource-
constrained devices will be challenging.
Keeping balance between maintaining the performance of
high-accurate services and the protection of user privacy
is noteworthy. Location information and identities are
needed to realize many smart applications. This requires
careful consideration of data access rights and ownership,
supervision and regulations for protecting privacy.
AI and machine learning (ML) technologies show a greater
impact on privacy in two ways [10]. In one way, the correct
application of ML can enhance privacy in 6G, whereas in
another way privacy violations may occur on ML attacks. The
privacy attacks on ML models can be occurred on training
(e.g., poisoning attack) and testing phases (e.g., reverse, mem-
bership interference, adversarial attacks).
E. New Technologies and Threat Landscapes
Considering the above technological, architectural and ap-
plication specific aspects of the future 6G networks, they
may encounter a wide range of security challenges as threat
landscapes. Since the attacks can be generalized based on
the technologies rather than the applications, we are taking
this step forward to give the reader an insight about the
most novel and specific attacks in 6G technologies (Table II).
The advent and advancements of technologies may also pave
the way to generate more powerful attackers who can create
sophisticated attacks on different parts of 6G architecture. In
addition to the attacks in Table II, each technology may also
face many variants of well-known attacks such as Distributed
DoS, MITM, sybil, scanning and spoofing attacks.
TABLE I: 6G Applications: Security requirement and Possible Challenges.
Security Requirements Expected Security and Implantation Challenges
Potential 6G Applications
Ultra Lightweight Security
Extremely Low latency
Extreme Scalability
Zero-touch Security
High Privacy
Proactive Security
Security via Edge
Domain specific security
Limited resources
Diversity of Devices
High Mobility
Physical Tempering
Terrorist Attacks
Intermittent Connectivity
Localized environment
Lack of Security Standards
E2E Security orchestration
Energy Efficiency
UAV based mobility M H H H L M H L H M H M H L L L H H
Connected Autonomous Vehicles L H H H M H H H L M H M H L L L H M
Smart Grid 2.0 H L H M M H L H H L L H H H L L L M
Collaborative Robots M H M H L L H H M L M M L L H L M M
Hyper-Intelligent Healthcare H H H M H M H H H H M M L M H M H H
Industry 5.0 M H H H L H H H H H M L M L H M H H
Extended Reality H H H M H L H L H M M H L L L H H H
LLow Level Requirement/Impact MMedium Level Requirement/Impact HHigh Level Requirement/Impact
TABLE II: Security threats and key 6G technologies.
Key Tech. Security Threat Description
AI Poisonous attacks Training data tampering via intentionally prepared malicious samples (e.g., manipulation of labelled data or weak
labelling), and thus influencing the learning outcomes and leading to misclassification and wrong regression
Evasion attacks Target the test phase by attempting to circumvent the learned model by injecting disorders to the test data.
ML API-based Attacks When an adversary queries and attack an API of a ML model to obtain predictions on input feature vectors. This
may include model inversion (recover training data), model extraction (reveal model architecture compromising
model confidentiality) and membership inference (exploit model output to predict on training data and ML model)
Infrastructure physical
attacks & communica-
tion tampering
Intentional outages and impairments in the communication and computational infrastructure lead to impairments
in decision-making/data processing and may even put entire AI systems offline.
Compromise of AI
Most AI solutions utilize existing AI/ML frameworks. Vulnerabilities in those artefacts or traditional attack vectors
towards their software, firmware and hardware environments (especially, cloud-centric operation) target integrity
of AI/ML functions.
DLT The eclipse attack pos-
When blockchain node communications are disrupted or disseminated, it may end up accepting false information
that may result in the confirmation of fake transactions.
Centralization of min-
ers (51% Attack)
Cybercriminals compromise public blockchain applications and acquire or gain control over at least 51% of its
mining power, they will be able to manipulate the blockchain.
End-user vulnerabili-
Individuals can lose or misplace their private keys, compromising their blockchain stored assets (e.g., identity theft,
malware, phishing attacks.).
Software Vulnerability When certain DLT projects deploy inadequately tested code on live blockchains, the vulnerabilities and bugs can
be detrimental to the decentralized model of many blockchain solutions.
Quantum cloning at-
Take a random quantum state of an information and make an exact copy without altering the original state of the
Quantum collision at-
A quantum collision attack occurs when two different inputs of a hash function provide the same output in a
quantum setting.
THz Access control attacks Adversaries break access controls, steal data or user credentials in order to access unauthorized resources or modify
system parameters.
Eavesdropping Although transmissions with high directionality in narrow beams are robust to interception attacks, there is still a
possibility for malicious nodes intercepting the signal
VLC Eavesdropping As vulnerable as RF when nodes are deployed in public areas and/or the presence of large windows in the coverage
areas, and in presence of cooperating eavesdroppers. Also, high throughput indoor VLC systems.
Jamming or data mod-
ification attacks
In VLC or hybrid VLC-RF systems, malicious transmitters can pass undetected. Highly directed transmitter, such
as by using optical beamforming techniques, increases the successful attack probability.
This section discusses 6G technologies and the related
security issues/ solutions(i.e., current and future work).
A. Distributed and Scalable AI/ML security
6G envisions autonomous networks which will perform
Self-X (self-configuration, self-monitoring, self-healing and
self-optimization) without minimal human involvement [11].
The ongoing specification efforts to integrate AI/ML as a
native element in future networks such as ETSI ZSM ar-
chitecture entailing closed-loop operation and AI/ML tech-
niques with pervasive automation of network management
operations including security are important steps towards that
goal [7]. Since the pervasive use of AI/ML will be realized
in a distributed and large-scale system for various use cases
including network management, distributed AI/ML techniques
are supposed to enforce rapid control and analytics on the
extremely large amount of generated data in 6G networks.
In 6G, AI/ML will be spatially pushed closer to the source
of data-of-interest for ultra-low latency while distributing ML
functions over the network to attain performance gains due to
optimized models and ensemble decision making. However,
overcoming practical constraints of some network elements
(e.g., IoT) such as computational shortcomings and intermit-
tent connectivity is an open challenge [4].
Distributed AI/ML can be used for security for different
phases of cybersecurity protection and defense in 6G. The
utility of AI/ML driven cybersecurity lies on the advantages in
terms of autonomy, higher accuracy and predictive capabilities
for security analytics. Nevertheless, there are also difficult
challenges for the pervasive use of AI/ML from the cybersecu-
rity aspect, either as cybersecurity enabler or a technique that
may lead to security issues under certain circumstances [12]:
- Trustworthiness An eager reliance on AI/ML in future
networks raises an evident question: Are ML components
trustworthy? This is a more important issue when critical
network functions including security are AI-controlled. For
this purpose, trusted computing enablers, formal verification
techniques and integrity checks are important tools.
- Visibility For controllability and accountability, visibility
is crucial. Security experts and monitoring require clear and
intelligible insight into AI based schemes, more than black-
box operation. A research question is how to timely monitor
for security-violating AI incidents.
- AI ethics and liability Once AI/ML is integrated into
6G security, one question becomes fairness and ethical AI:
Does AI based optimization starve some users or applications?
Specifically, for security, the question becomes whether AI
driven security solutions protect all users the same. Another
vague point is Who is liable if AI controlled security functions
fail. Liability management is a complicated task with au-
tonomous entities operating in an ICT environment, including
6G security operations.
- Scalability and feasibility For distributed ML setups such
as federated learning, data transmissions should be secured
and preserve privacy. For AI/ML controlled security functions,
scalability is challenging in terms of required computation,
communication and storage resources. For instance, FeMBB
leads to huge data flows. Integrated with AI/ML based security
controls, these flows may cause significant overhead.
- Model and data resilience Models should be secured
and robust in the learning and inference phases (e.g., against
poisoning attacks). Blockchain is a potential remedy for a dis-
tributed, transparent and secure data sharing framework [13].
- Privacy Different ML techniques (e.g., neural networks,
deep learning, supervised learning) can be applied for privacy
protection in terms of data, image, location, and communica-
tion (e.g., Android, intelligent vehicles, IoT).
B. Distributed Ledger Technology (DLT)
As a DLT, recently Blockchain has gained the highest
attention in the telecommunication industry. The added advan-
tages of DLTs such as disintermediation, immutability, non-
repudiation, proof of provenance, integrity and pseudonymity
are particularly important to enable different services in 6G
networks with trust and security [14]. The use of AI/ML,
and other data analytic technologies, can be a source for
new attack vectors (e.g., poisoning attacks in training phase,
evasion attacks in testing phase) [15]. Since data is the
facilitator of AI algorithms, it is crucial to ensure their integrity
and provenance from the trusted sources [16]. DLT has the
potential of protecting the integrity of AI data via immutable
records and distributed trust between different stakeholders,
by enabling the confidence in AI-driven systems in a multi-
tenant/multi-domain environment.
While trust provides the needed confidence for users for
adopting autonomic AI based security management systems
in 6G networks, it may not prevent their breach and failure
in AI based systems. Thus, to prevent the failure of AI
systems, liability and the responsibility should be carefully
addressed. Therefore, trust with liability are complementing
to ensure E2E secured service delivery in 6G networks. DLT
based Smart contracts can be utilized to define Trust Level
Agreement (TLA) [17] and liability of each party or between
components in case of TLA violations.
Furthermore, in order to support the role of DLT/blockchain
to comply with 6G requirements, most of the current 5G
service models need to be significantly evolved. For instance
DLT can be used in secure VNF management, secure slice
brokering, automated Security SLA management, scalable
IoT PKI management, and secure roaming and offloading
handling [14]. Blockchain is also a key candidate for pri-
vacy preservation in content-centric 6G networks. Having a
common communication channel in blockchain may allow
network users to be identified by pseudo names instead of
direct personal identities or location information.
C. Quantum security
Quantum computing is envisioned to use in 6G commu-
nication networks for detection, mitigation and prevention of
security vulnerabilities. Quantum computing assisted commu-
nication is a novel research area that investigates the possi-
bilities of replacing quantum channels with noiseless classical
communication channels to achieve extremely high reliability
in 6G. With the advancements of quantum computing, it is
foreseen that quantum-safe cryptography should be introduced
in the post-quantum world. The discrete logrithmic problem,
which is the basis of current asymmetric cryptography, may
become solvable in polynomial time with the development of
quantum algorithms (e.g., Shor) [18].
Since quantum computing tends to use the quantum nature
of information, it may intrinsically provide absolute random-
ness and security to improve the transmission quality [18].
Integrating post-quantum cryptography schemes with physical
layer security schemes may ensure secure 6G communication
links. Novel research eras may open up by introducing ML-
based cyber-security and quantum encryption in communi-
cation links in 6G networks. Quantum ML algorithms may
enhance security and privacy in communication networks with
the quantum improvements in supervised and unsupervised
learning for clustering and classification tasks. There are
promising 6G applications where there are potentials in ap-
plying quantum security mechanisms. For instance, many 6G
applications such as ocean communication, satellite communi-
cation, terrestrial wireless networks, and THz communications
systems have potentials of using quantum communication
protocols such as quantum key distribution (QKD) [19]. QKD
is applicable in the conventional key distribution schemes
by providing quantum mechanics to establish a secret key
between two legitimate parties.
D. Physical Layer Security (PLS)
Since security mechanisms are embedded in different layers
of a network, they can be used jointly across these layers
to implement redundant protection or in a subset of layers
for resource-constrained applications. PLS methods will be
leveraged by 6G to provide an adaptive additional layer of
protection in the context of new enabling technologies, as
discussed next.
1) TeraHertz (THz) technology: THz communication (1
GHz to 10 THz) is envisioned to be a key technology for
6G. In such frequencies, there exist an increased directionality
of transmitted signals that allows to confine unauthorized
users to be on the same narrow path of the legitimate user
for intercepting signals, thus offering stronger security at
the physical layer. However, the authors in [20] prove that
an eavesdropper can also intercept signals, in line-of-sight
(LoS) transmissions, by placing an object in the path of the
transmission to scatter radiation towards him. A countermea-
sure against this eavesdropping technique, which works by
characterizing the backscatter of the channel, was designed in
order to detect some, although not all, eavesdroppers. Indeed,
THz communications are prone to access control attacks,
malicious behavior, and data transmission exposure. Then, new
PLS solutions are required for secure THz transmissions, e.g.,
electromagnetic signature of materials and devices at THz
frequencies can be used for authentication methods [3].
2) Visible Light Communication (VLC) technology: VLC is
an optical wireless technology that has attracted high interest
due to its advantages compared to radio frequency (RF)
systems, such as high data rates, large available spectrum,
robustness against interference, and inherent security. VLC
systems can offer a higher level of security compared to
RF systems due to the fact that light cannot penetrate walls.
However, due to the broadcast nature and LoS propagation
of VLC systems, they are also vulnerable to eavesdropping
from unauthorized nodes located in the coverage area of trans-
mitters. Confidentiality of VLC systems is a crucial issue for
the design of practical VLC systems, where PLS techniques
can provide interesting solutions. For instance, the accurate
localization capabilities of VLC joint with ML techniques can
be used for anomaly detection [21].
3) Molecular communication (MC): In MC, bionanoma-
chines communicate using chemical signals or molecules in
an aqueous environment, thus being a promising technology
for 6G in many healthcare applications. However, MC tackles
highly sensitive information, with several security and privacy
challenges related to the communication, authentication and
encryption process, thus providing secure MC is imperative.
Therefore, the notion of biochemical cryptography was intro-
duced in [22], where a biological macro-molecule composition
and structure could be utilized as a medium to maintain
information integrity. In [23], the primary benefits and limits
of PLS in diffusion-based channels are investigated, where the
secrecy capacity is derived to obtain insights on the number
of secure symbols a diffusion-based channel can afford.
This paper summarized the envisioned main requirements,
paradigms, new architectural challenges, new applications, and
enabling technologies that are expected to shape the future
generation of wireless networks, 6G, from the perspective of
the security and privacy challenges. Herein, we provided our
vision on the new threat landscape expected for these networks
as well as the promising security solutions and technologies
that have the potential to evolve and be part of a holistic
solution to protect 6G networks. However, as the specifications
of 6G networks have not yet been defined, there is not adequate
literature to support very insightful discussions. In future,
we intend to make a more detailed survey to investigate the
security and privacy aspects of 6G and related technologies.
This work is supported by 6Genesis Flagship (grant 318927)
and 5GEAR projects. The research leading to these results
partly received funding from European Union’s Horizon 2020
research and innovation programme under grant agreement no
871808 (5G PPP project INSPIRE-5Gplus). The paper reflects
only the authors’ views. The Commission is not responsible
for any use that may be made of the information it contains.
[1] C. de Alwis, A. Kalla, Q. V. Pham, P. Kumar, K. Dev, W. J. Hwang,
and M. Liyanage, “Survey on 6G Frontiers: Trends, Applications,
Requirements, Technologies and Future Research,IEEE Open Journal
of the Communications Society, pp. 1–1, 2021.
[2] G. Gui, M. Liu, F. Tang, N. Kato, and F. Adachi, “6G: Opening new
horizons for integration of comfort, security and intelligence,” IEEE
Wireless Communications, 2020.
[3] M. Wang, T. Zhu, T. Zhang, J. Zhang, S. Yu, and W. Zhou, “Security
and privacy in 6G networks: New areas and new challenges,Digital
Communications and Networks, vol. 6, no. 3, pp. 281–291, 2020.
[4] G. Plastiras, M. Terzi, C. Kyrkou, and T. Theocharidcs, “Edge intelli-
gence: Challenges and opportunities of near-sensor machine learning ap-
plications,” in 2018 IEEE 29th International Conference on Application-
specific Systems, Architectures and Processors (ASAP), 2018, pp. 1–7.
[5] N. Khurana, S. Mittal, A. Piplai, and A. Joshi, “Preventing poisoning
attacks on AI based threat intelligence systems,” in 2019 IEEE 29th
International Workshop on Machine Learning for Signal Processing
(MLSP). IEEE, 2019, pp. 1–6.
[6] M. Pawlicki, M. Chora´
s, and R. Kozik, “Defending network intrusion
detection systems against adversarial evasion attacks,Future Genera-
tion Computer Systems, vol. 110, pp. 148–154, 2020.
[7] ETSI ISG ZSM, “ETSI GS ZSM 002: ZSM reference architecture,”
2019. [Online]. Available: gs/ZSM/
001 099/002/01.01.01 60/gs ZSM002v010101p.pdf
[8] C. Benzaid and T. Taleb, “ZSM security: Threat surface and best
practices,” IEEE Network, vol. 34, no. 3, pp. 124–133, 2020.
[9] X. You, C.-X. Wang, J. Huang, X. Gao, Z. Zhang, M. Wang, Y. Huang,
C. Zhang, Y. Jiang, J. Wang et al., “Towards 6G wireless communication
networks: Vision, enabling technologies, and new paradigm shifts,”
Science China Information Sciences, vol. 64, no. 1, pp. 1–74, 2021.
[10] Y. Sun, J. Liu, J. Wang, Y. Cao, and N. Kato, “When machine learning
meets privacy in 6G: A survey,” IEEE Communications Surveys &
Tutorials, vol. 22, no. 4, 2020.
[11] S. Zhang and D. Zhu, “Towards artificial intelligence enabled 6G: State
of the art, challenges, and opportunities,” Computer Networks, vol. 183,
p. 107556, 2020.
[12] ENISA, “Artificial intelligence cybersecurity challenges,” ENISA, Tech.
Rep., December 2020.
[13] W. Li, Z. Su, R. Li, K. Zhang, and Y. Wang, “Blockchain-based data
security for artificial intelligence applications in 6G networks,” IEEE
Network, vol. 34, no. 6, pp. 31–37, 2020.
[14] T. Hewa, G. G¨
ur, A. Kalla, M. Ylianttila, A. Bracken, and M. Liyanage,
“The role of blockchain in 6G: Challenges, opportunities and research
directions,” in 2020 2nd 6G Wireless Summit. IEEE, 2020.
[15] S. Nayak and R. Patgiri, “6G Communication Technology: A Vision on
Intelligent Healthcare,” arXiv e-prints, p. arXiv:2005.07532, Apr. 2020.
[16] H. Kim, J. Park, M. Bennis, and S.-L. Kim, “On-device feder-
ated learning via blockchain and its latency analysis,” arXiv preprint
arXiv:1808.03949, 2018.
[17] P. Varalakshmi and T. Judgi, “Multifaceted trust management framework
based on a trust level agreement in a collaborative cloud,Computers
& Electrical Engineering, vol. 59, pp. 110–125, 2017.
[18] S. J. Nawaz, S. K. Sharma, S. Wyne, M. N. Patwary, and M. Asaduz-
zaman, “Quantum machine learning for 6G communication networks:
State-of-the-art and vision for the future,” IEEE Access, vol. 7, 2019.
[19] S. Tarantino, B. Da Lio, D. Cozzolino, and D. Bacco, “Feasibility of
quantum communications in aquatic scenarios,” Optik, p. 164639, 2020.
[20] J. Ma, R. Shrestha, J. Adelberg, C.-Y. Yeh, E. K. Zahed Hossain, J. M.
Jornet, and D. M. Mittleman, “Security and eavesdropping in terahertz
wireless links,” Nature, vol. 563, no. 8, pp. 89–93, 2018.
[21] M. A. Arfaoui, M. D. Soltani, I. Tavakkolnia, A. Ghrayeb, M. Safari,
C. M. Assi, and H. Haas, “Physical layer security for visible light
communication systems: A survey,IEEE Communications Surveys
Tutorials, vol. 22, no. 3, pp. 1887–1908, 2020.
[22] F. Dressler and F. Kargl, “Towards security in nano-communication:
Challenges and opportunities,” Nano Communication Networks, vol. 3,
no. 3, pp. 151 – 160, 2012.
[23] L. Mucchi, A. Martinelli, S. Jayousi, S. Caputo, and M. Pierobon,
“Secrecy capacity and secure distance for diffusion-based molecular
communication systems,” IEEE Access, vol. 7, 2019.
... Fortunately, several research groups in the wireless research community study the main potential security issue related to AI-based algorithms, i.e., model poising [15], [16]. The authors in [17], [18] provided a comprehensive review of NextG wireless networks in terms of opportunities and security and privacy challenges, as well as proposed solutions for NextG networks.Several studies also present robust frameworks focusing on detecting adversarial attacks accurately. The authors in [19] proposed a framework to detect adversarial attacks for industrial artificial intelligence systems (IAISs), called DeSVig, i.e., decentralized swift vigilance framework. ...
Full-text available
Future wireless networks (5G and beyond), also known as Next Generation or NextG, are the vision of forthcoming cellular systems, connecting billions of devices and people together. In the last decades, cellular networks have dramatically grown with advanced telecommunication technologies for high-speed data transmission, high cell capacity, and low latency. The main goal of those technologies is to support a wide range of new applications, such as virtual reality, metaverse, telehealth, online education, autonomous and flying vehicles, smart cities, smart grids, advanced manufacturing, and many more. The key motivation of NextG networks is to meet the high demand for those applications by improving and optimizing network functions. Artificial Intelligence (AI) has a high potential to achieve these requirements by being integrated into applications throughout all network layers. However, the security concerns on network functions of NextG using AI-based models, i.e., model poising, have not been investigated deeply. It is crucial to protect the next-generation cellular networks against cybersecurity threats, especially adversarial attacks. Therefore, it needs to design efficient mitigation techniques and secure solutions for NextG networks using AI-based methods. This paper proposes a comprehensive vulnerability analysis of deep learning (DL)-based channel estimation models trained with the dataset obtained from MATLAB’s 5G toolbox for adversarial attacks and defensive distillation-based mitigation methods. The adversarial attacks produce faulty results by manipulating trained DL-based models for channel estimation in NextG networks while making models more robust against attacks through mitigation methods. This paper also presents the performance of the proposed defensive distillation mitigation method for each adversarial attack. The results indicate that the proposed mitigation method can defend the DL-based channel estimation models against adversarial attacks in NextG networks.
... Fortunately, the main potential security issue related to AI-based algorithms, i.e., model poising, is studied by several research groups in the wireless research community [15], [16]. The authors of [17], [18] provided a comprehensive review of NextG wireless networks in terms of opportunities, and security and privacy challenges as well as proposes solutions for NextG networks. ...
Full-text available
Future wireless networks (5G and beyond) are the vision of forthcoming cellular systems, connecting billions of devices and people together. In the last decades, cellular networks have been dramatically growth with advanced telecommunication technologies for high-speed data transmission, high cell capacity, and low latency. The main goal of those technologies is to support a wide range of new applications, such as virtual reality, metaverse, telehealth, online education, autonomous and flying vehicles, smart cities, smart grids, advanced manufacturing, and many more. The key motivation of NextG networks is to meet the high demand for those applications by improving and optimizing network functions. Artificial Intelligence (AI) has a high potential to achieve these requirements by being integrated in applications throughout all layers of the network. However, the security concerns on network functions of NextG using AI-based models, i.e., model poising, have not been investigated deeply. Therefore, it needs to design efficient mitigation techniques and secure solutions for NextG networks using AI-based methods. This paper proposes a comprehensive vulnerability analysis of deep learning (DL)-based channel estimation models trained with the dataset obtained from MATLAB's 5G toolbox for adversarial attacks and defensive distillation-based mitigation methods. The adversarial attacks produce faulty results by manipulating trained DL-based models for channel estimation in NextG networks, while making models more robust against any attacks through mitigation methods. This paper also presents the performance of the proposed defensive distillation mitigation method for each adversarial attack against the channel estimation model. The results indicated that the proposed mitigation method can defend the DL-based channel estimation models against adversarial attacks in NextG networks.
... Porambage [3] discussed 6G security challenges with various 6G applications, such as trust management problem in smart grid, scalability and automation issue industry 5.0, fake experiences in extended reality, privacy protection in holographic telepresence, and unarmed aerial vehicle (UAV)-based mobility. Furthermore, they explored distributed ledger technology, quantum computing, and scalable AI/machine learning (ML) technologies with 6G and identified how it affects the security and privacy of 6G [47]. Despite the fact that the 6G network has indispensable capabilities, the security problem continues to hinder the end-user experience. ...
Full-text available
The emerging need for high data rate, low latency, and high network capacity encourages wireless networks (WNs) to build intelligent and dynamic services, such as intelligent transportation systems, smart homes, smart cities, industrial automation, etc. However, the WN is impeded by several security threats, such as data manipulation, denial-of-service, injection, man-in-the-middle, session hijacking attacks, etc., that deteriorate the security performance of the aforementioned WN-based intelligent services. Toward this goal, various security solutions, such as cryptography, artificial intelligence (AI), access control, authentication, etc., are proposed by the scientific community around the world; however, they do not have full potential in tackling the aforementioned security issues. Therefore, it necessitates a technology, i.e., a blockchain, that offers decentralization, immutability, transparency, and security to protect the WN from security threats. Motivated by these facts, this paper presents a WNs survey in the context of security and privacy issues with blockchain-based solutions. First, we analyzed the existing research works and highlighted security requirements, security issues in a different generation of WN (4G, 5G, and 6G), and a comparative analysis of existing security solutions. Then, we showcased the influence of blockchain technology and prepared an exhaustive taxonomy for blockchain-enabled security solutions in WN. Further, we also proposed a blockchain and a 6G-based WN architecture to highlight the importance of blockchain technology in WN. Moreover, the proposed architecture is evaluated against different performance metrics, such as scalability, packet loss ratio, and latency. Finally, we discuss various open issues and research challenges for blockchain-based WNs solutions.
Full-text available
Industry 4.0 has been provided for the last 10 years to benefit the industry and the shortcomings; finally, the time for industry 5.0 has arrived. Smart factories are increasing the business productivity; therefore, industry 4.0 has limitations. In this paper, there is a discussion of the industry 5.0 opportunities as well as limitations and the future research prospects. Industry 5.0 is changing paradigm and brings the resolution since it will decrease emphasis on the technology and assume that the potential for progress is based on collaboration among the humans and machines. The industrial revolution is improving customer satisfaction by utilizing personalized products. In modern business with the paid technological developments, industry 5.0 is required for gaining competitive advantages as well as economic growth for the factory. The paper is aimed to analyze the potential applications of industry 5.0. At first, there is a discussion of the definitions of industry 5.0 and advanced technologies required in this industry revolution. There is also discussion of the applications enabled in industry 5.0 like healthcare, supply chain, production in manufacturing, cloud manufacturing, etc. The technologies discussed in this paper are big data analytics, Internet of Things, collaborative robots, Blockchain, digital twins and future 6G systems. The study also included difficulties and issues examined in this paper head to comprehend the issues caused by organizations among the robots and people in the assembly line.
The sixth-generation (6G) technology of mobile networks will establish new standards to fulfill unreachable performance requirements by fifth-generation (5G) mobile networks. This is due to the high requirements for more intelligent network, ultra-lower latency, extreme network communication speed, and supporting massive number of various connected applications. In the long term, the convergence of various business developments with communication platforms, as initiated by 5G, will exaggerate and highlight areas where 5G's capabilities will fall short of performance requirements. Motivated by the development of applications in massive connections, future networks, developments, and technological advancements for mobile communications that go beyond fifth-generation (B5G) networks are being developed. In this context, highly immersive applications are demanded, such as three-dimensional (3D) communications, digital twins, or massive extended reality (XR)/virtual reality (VR) applications, which will need 6G capabilities to be realized at scale to be commercially feasible. Mainly, we anticipate that only the upcoming 6G networks will be capable of running extremely high-performance connectivity with massive numbers of connected devices, even under laborious scenarios such as extreme density, diverse mobility, and energetic environments. In this article, we look at the most recent trends and future emerging trends that are possible to operate 6G network. Paper aims to provide more inclusive and brief review about 6G mobile communication technology in one survey paper. Initially, a comprehensive overview of the 6G system is introduced in terms of visions, drivers, requirements, architecture, and usage scenarios required to enable 6G applications. After that, the opportunities and advantages of 6G mobile technology has been discussed. Further, the promising new techniques that enable 6G technology has been highlighted. This is followed by a potential discussion of challenges and research directions. This article is envisioned to serve as an informative guideline to stimulate interest and further studies for subsequent research and development of 6G networks. Paper will enable the readers to briefly figure out the key requirements, targets, that will be need and the applications, advantages, and opportunities that can be offered as well as the challenges that need to be addressed before the implementation of this new technology.
Conference Paper
Full-text available
Fingerprint Enhancement Algorithm for Access Control Identification, is an emerging system that provides good and efficient service for access thought out. It plays a very important feature in providing access anywhere in the world. There are so many issues around it and solutions have been implemented but failed. This is because of the interruptions on the system which are due to the over ink, dry skin, cut, bruises, and fingerprint misalignments. As a result, this paper proposes a fingerprint identification algorithm or verification system that will be of good quality for the input fingerprint images. The proposed Efficient Fingerprint Enhancement (EFE) algorithm will overcome any possible limitations that have been found in the current biometric systems. The proposed EFE algorithm is going to bring improvement on the clarity of the ridges. In addition, the proposed EFE algorithm will bring improvement on the valley structures to the input fingerprint images which are based solely on the frequency and local ridge orientation. The MATLAB simulation tool will be used in the future to evaluate the performance of the proposed EFE algorithm with regards to improving the quality of inaccurate and askew fingerprint image during the authentication.
Full-text available
To date, 5G (5th generation of mobile communications) roll out has been going on for more than two years, and the most of it has still to come. Meanwhile, Key Performance Indicators (KPIs) and Key Enabling Technologies (KETs) of Beyond-5G (B5G) and 6G (6th generation of mobile communications) are already at stake, looking at 2030. Future networks will leverage autonomous and evolutionary characteristics, triggered by the cornerstone of Artificial Intelligence (AI), falling well-beyond the scopes of 5G. Besides, seamless increase of KPIs, across the transition from 5G to 6G, with 100-1000 times higher data rate per user, latency reduction and reliability improvement, also stepping into the domain of (sub-)THz and optical communications, will set unparalleled demands for Hardware (HW) systems and components. This work focuses on the envisaged gap existing between currently in use strategies for design of Hardware-Software (HW-SW) systems and what the AI-driven 6G will demand, in terms of adaptivity, flexibility and evolution. An important part is forecasted for Micro/Nano technologies, devices and systems, in enabling 6G functionalities, especially at the network edge, stimulating partial reconceptualization of the classical idea of HW, in fact, rising its level of abstraction.
Full-text available
Faced with the rapid increase in smart Internet-of-Things (IoT) devices and the high demand for new business-oriented services in the fifth-generation (5G) and beyond network, the management of mobile networks is getting complex. Thus, traditional Network Management and Orchestration (MANO) approaches cannot keep up with rapidly evolving application requirements. This challenge has motivated the adoption of the Zero-touch network and Service Management (ZSM) concept to adapt the automation into network services management. By automating network and service management, ZSM offers efficiency to control network resources and enhance network performance visibility. The ultimate target of the ZSM concept is to enable an autonomous network system capable of self-configuration, self-monitoring, self-healing, and self-optimization based on service-level policies and rules without human intervention. Thus, the paper focuses on conducting a comprehensive survey of E2E ZSM architecture and solutions for 5G and beyond networks. The article begins by presenting the fundamental ZSM architecture and its essential components and interfaces. Then, a comprehensive review of the state-of-the-art for key technical areas, i.e., ZSM automation, cross-domain E2E service lifecycle management, and security aspects, are presented. Furthermore, the paper contains a summary of recent standardization efforts and research projects toward the ZSM realization in 5G and beyond networks. Finally, several lessons learned from the literature and open research problems related to ZSM realization are also discussed in this paper.
Full-text available
Emerging applications such as Internet of Everything , Holographic Telepresence, collaborative robots, and space and deep-sea tourism are already highlighting the limitations of existing fifth-generation (5G) mobile networks. These limitations are in terms of data-rate, latency, reliability, availability, processing, connection density and global coverage, spanning over ground, underwater and space. The sixth-generation (6G) of mobile networks are expected to burgeon in the coming decade to address these limitations. The development of 6G vision, applications , technologies and standards has already become a popular research theme in academia and the industry. In this paper, we provide a comprehensive survey of the current developments towards 6G. We highlight the societal and technological trends that initiate the drive towards 6G. Emerging applications to realize the demands raised by 6G driving trends are discussed subsequently. We also elaborate the requirements that are necessary to realize the 6G applications. Then we present the key enabling technologies in detail. We also outline current research projects and activities including standardization efforts towards the development of 6G. Finally, we summarize lessons learned from state-of-the-art research and discuss technical challenges that would shed a new light on future research directions towards 6G.
Full-text available
The fifth generation (5G) wireless communication networks are being deployed worldwide from 2020 and more capabilities are in the process of being standardized, such as mass connectivity, ultra-reliability, and guaranteed low latency. However, 5G will not meet all requirements of the future in 2030 and beyond, and sixth generation (6G) wireless communication networks are expected to provide global coverage, enhanced spectral/energy/cost efficiency, better intelligence level and security, etc. To meet these requirements, 6G networks will rely on new enabling technologies, i.e., air interface and transmission technologies and novel network architecture, such as waveform design, multiple access, channel coding schemes, multi-antenna technologies, network slicing, cell-free architecture, and cloud/fog/edge computing. Our vision on 6G is that it will have four new paradigm shifts. First, to satisfy the requirement of global coverage, 6G will not be limited to terrestrial communication networks, which will need to be complemented with non-terrestrial networks such as satellite and unmanned aerial vehicle (UAV) communication networks, thus achieving a space-air-ground-sea integrated communication network. Second, all spectra will be fully explored to further increase data rates and connection density, including the sub-6 GHz, millimeter wave (mmWave), terahertz (THz), and optical frequency bands. Third, facing the big datasets generated by the use of extremely heterogeneous networks, diverse communication scenarios, large numbers of antennas, wide bandwidths, and new service requirements, 6G networks will enable a new range of smart applications with the aid of artificial intelligence (AI) and big data technologies. Fourth, network security will have to be strengthened when developing 6G networks. This article provides a comprehensive survey of recent advances and future trends in these four aspects. Clearly, 6G with additional technical requirements beyond those of 5G will enable faster and further communications to the extent that the boundary between physical and cyber worlds disappears.
Full-text available
As more and more 5G networks are deployed, the limitations of 5G networks are not only being discovered but are driving exploratory research into 6G networks as a next-generation solution. Part of these investigations includes the fundamental security and privacy problems associated with 6G technologies. Therefore, to consolidate and solidify this foundational research as a basis for future investigations, we have prepared this survey on the current state-of-play in 6G-related security and privacy. The survey begins with a historical review of previous network technologies and how they have informed the current trends in 6G networking. We then discuss four key aspects of 6G networks – real-time intelligent edge computing, distributed artificial intelligence, intelligent radio, and 3D intercoms – and some promising emerging technologies in each area, along with the relevant security and privacy issues. The survey concludes with a report on potential 6G applications. Some of the references used in this paper along with further details of several points raised can be found at:
6G is a promising communication technology that will dominate the entire health market from 2030 onward. It will dominate not only health sector but also diverse sectors. It is expected that 6G will revolutionize many sectors including healthcare. Healthcare will be fully AI-driven and dependent on 6G communication technology, which will change our perception of lifestyle. Currently, time and space are the key barriers to health care and 6G will be able to overcome these barriers. Also, 6G will be proven as a game changing technology for healthcare. Therefore, in this perspective, we envision healthcare system for the era of 6G communication technology. Also, various new methodologies have to be introduced to enhance our lifestyle, which is addressed in this perspective, including Quality of Life (QoL), Intelligent Wearable Devices (IWD), Intelligent Internet of Medical Things (IIoMT), Hospital-to-Home (H2H) services, and new business model. In addition, we expose the role of 6G communication technology in telesurgery, Epidemic and Pandemic.
The sixth generation (6G) networks are expected to provide a fully connected world with terrestrial wireless and satellite communications integration. The design concept of 6G networks is to leverage artificial intelligence (Ai) to promote the intelligent and agile development of network services. intelligent services inevitably involve the processing of large amounts of data, such as storage, computing, and analysis, such that the data may be vulnerable to tampering or contamination by attackers. in this article, we propose a blockchain-based data security scheme for Ai applications in 6G networks. Specifically, we first introduce the 6G architecture (i.e., a space-air-ground-underwater integrated network). Then we discuss two Ai-enabled applications, indoor positioning and autonomous vehicle, in the context of 6G. Through a case study of an indoor navigation system, we demonstrate the effectiveness of blockchain in data security. The integration of Ai and blockchain is developed to evaluate and optimize the quality of intelligent service. Finally, we discuss several open issues about data security in the upcoming 6G networks.
6G is expected to support the unprecedented Internet of everything scenarios with extremely diverse and challenging requirements. To fulfill such diverse requirements efficiently, 6G is envisioned to be space-aerial-terrestrial-ocean integrated three-dimension networks with different types of slices enabled by new technologies and paradigms to make the system more intelligent and flexible. As 6G networks are increasingly complex, heterogeneous and dynamic, it is very challenging to achieve efficient resource utilization, seamless user experience, automatic management and orchestration. With the advancement of big data processing technology, computing power and the availability of rich data, it is natural to tackle complex 6G network issues by leveraging artificial intelligence (AI). In this paper, we make a comprehensive survey about AI-empowered networks evolving towards 6G. We first present the vision of AI-enabled 6G system, the driving forces of introducing AI into 6G and the state of the art in machine learning. Then applying machine learning techniques to major 6G network issues including advanced radio interface, intelligent traffic control, security protection, management and orchestration, and network optimization is extensively discussed. Moreover, the latest progress of major standardization initiatives and industry research programs on applying machine learning to mobile networks evolving towards 6G are reviewed. Finally, we identify important open issues to inspire further studies towards an intelligent, efficient and secure 6G system.
The rapid-developing Artificial Intelligence (AI) technology, fast-growing network traffic, and emerging intelligent applications (e.g., autonomous driving, virtual reality, etc.) urgently require a new, faster, more reliable and flexible network form. At this time, researchers in both industry and academia have turned their attention to the sixth generation (6G) communication networks. In the 6G vision, various intelligent application scenarios that utilize Machine Learning (ML) technology (the most important branch of AI) will bring rich heterogeneous connections, as well as massive information storage and operations. When ML meets 6G, new opportunities will emerge along with numerous privacy challenges. On one hand, a secure ML structure, or the correct application of ML, can protect privacy in 6G. On the other hand, ML may be attacked or abused, resulting in privacy violation. It is worth noting that the alliance between 6G and ML may also be a double-edged sword in many cases, rather than absolutely infringe or protect privacy. Therefore, based on lots of existing meaningful works, this paper aims to provide a comprehensive survey of ML and privacy in 6G, with a view to further promoting the development of 6G and privacy protection technologies.
Exchanging information in the aquatic environment represents a challenging but yet necessary task for example in military and scientific applications. Quantum cryptography is an already available solution able to guarantee information theoretic secure communication in multiple environment, i.e. free-space, fiber and space link. Yet, the implementation of quantum communications in the aquatic scenario is still a relatively new and unexplored field of research. This paper provides a feasibility analysis of various quantum key distribution protocols simulated in the water medium, by performing an evaluation of their secret key rate, external noise sources and wind effect on the surface of the water. Three different links are considered: line-of-sight, non line-of-sight and free-space to underwater channels. The outcomes of this analysis suggest that underwater quantum communication can be implemented by adopting several protocols in all three scenarios.
Due to the dramatic increase in high data rate services and in order to meet the demands of the fifth-generation (5G) networks, researchers from both academia and industry are exploring advanced transmission techniques, new network architectures and new frequency spectrum such as the visible light and the millimeter wave (mmWave) spectra. Visible light communication (VLC) particularly is an emerging technology that has been introduced as a promising solution for 5G and beyond, owing to the large unexploited spectrum, which translates to significantly high data rates. Although VLC systems are more immune against interference and less susceptible to security vulnerabilities since light does not penetrate through walls, security issues arise naturally in VLC channels due to their open and broadcasting nature, compared to fiber-optic systems. In addition, since VLC is considered to be an enabling technology for 5G, and security is one of the 5G fundamental requirements, security issues should be carefully addressed and resolved in the VLC context. On the other hand, due to the success of physical layer security (PLS) in improving the security of radio-frequency (RF) wireless networks, extending such PLS techniques to VLC systems has been of great interest. Only two survey papers on security in VLC have been published in the literature. However, a comparative and unified survey on PLS for VLC from information theoretic and signal processing point of views is still missing. This paper covers almost all aspects of PLS for VLC, including different channel models, input distributions, network configurations, precoding/signaling strategies, and secrecy capacity and information rates. Furthermore, we propose a number of timely and open research directions for PLS-VLC systems, including the application of measurement-based indoor and outdoor channel models, incorporating user mobility and device orientation into the channel model, and combining VLC and RF systems to realize the potential of such technologies.
Intrusion Detection and the ability to detect attacks is a crucial aspect to ensure cybersecurity. However, what if an IDS (Intrusion Detection System) itself is attacked; in other words what defends the defender? In this work, the focus is on countering attacks on machine learning-based cyberattack detectors. In principle, we propose the adversarial machine learning detection solution. Indeed, contemporary machine learning algorithms have not been designed bearing in mind the adversarial nature of the environments they are deployed in. Thus, Machine Learning solutions are currently the target of a range of attacks. This paper evaluates the possibility of deteriorating the performance of a well-optimised intrusion detection algorithm at test time by crafting adversarial attacks with the four of the recently proposed methods and then offers a way to detect those attacks. The relevant background is provided for both artificial neural networks and four ways of crafting adversarial attacks. The new detection method is explained in detail, and the results of five different classifiers are compared. To the best of our knowledge, detecting adversarial attacks on artificial neural networks has not yet been widely researched in the context of intrusion detection systems.