FIGURE 7 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
An illustration of 4 trained SC-SVM models that correspond to linear, RBF, polynomial (degree 3), and sigmoid kernels. markers are the ATD points associated with the label (#0). The brown area is the area that contains most of the ATD points .
Source publication
This paper presents a framework for converting wireless signals into structured datasets, which can be fed into machine learning algorithms for the detection of active eavesdropping attacks at the physical layer. More specifically, a wireless communication system, which consists of an access point (AP), K legitimate users and an active eavesdropper...
Similar publications
In this paper, we investigate an innovative physical layer security (PLS) scheme for an uncertain reconfigurable intelligent surface- (RIS-) assisted communication system under eavesdropping attack. Specifically, in our proposed system, we consider that the uncertain RIS is known to the legitimate user while not to the eavesdropper (Eve). In this m...
In this paper, we consider information transmission over a three-node physical layer security system. Based on the imperfect estimations of the main channel and the eavesdropping channel, we propose reducing the outage probability and interception probability by hindering transmissions in cases where the main channel is too strong or too weak, whic...
Hybrid communication systems, where millimeter-wave (mmWave) links coexist with microwave links, have been an essential component in the fifth-generation (5G) wireless networks. Nevertheless, the open feature of the wireless medium makes hybrid systems vulnerable to eavesdropping attacks. Eavesdroppers in hybrid communication systems can enhance th...
Distributed deployment for integrated sensing and communication (ISAC) can improve the sensing accuracy by exploring spatial diversity for covering the target state. However, secure fusion and limited energy consumption are still challenges for wireless-transmission-based distributed ISAC. In this paper, a secure decision-fusion scheme under energy...
Standard cryptography is expected to poorly fit IoT applications and services, as IoT devices can hardly cope with the computational complexity often required to run encryption algorithms. In this framework, physical layer security is often claimed as an effective solution to enforce secrecy in IoT systems. It relies on wireless channel characteris...
Citations
... A promising research direction for designing jammingresilient systems involves interference mitigation using learning techniques or multiple-input multiple-output (MIMO) techniques for detection and decoding data packets in the face of jamming signals [102]- [104] (P2 & P3). Strategies to overcome eavesdropping and to increase the secrecy capacity include secret coding and encryption [105], reciprocity-based key establishment [106], QKD schemes based on quantum physics, ensuring secrecy irrespective of the attacker's computing power [107]- [109], and using ML to detect active eavesdroppers [96], [110] (P1 & P2). Additionally, in recent years, intelligent reconfigurable surfaces (RISs) have been extensively studied as a means to cope with the inherent random nature of the wireless channel by directly manipulating/shaping it [111]- [113]. ...
The sixth generation (6G) mobile communication networks are expected to intelligently integrate into various aspects of modern digital society, including smart cities, homes, healthcare, transportation, and factories. While offering a multitude of services, it is likely that societies become increasingly reliant on 6G infrastructure. Any disruption to these digital services, whether due to human or technical failures, natural disasters, or terrorism, would significantly impact citizens' daily lives. Hence, 6G networks need not only to provide high-performance services but also to be resilient in maintaining essential services in the face of potentially unknown challenges. This paper introduces a comprehensive concept for designing resilient 6G communication networks, summarizing our initial studies within the German Open6GHub project. Adopting an interdisciplinary approach, we propose to embed physical and cyber resilience across all communication system layers, addressing electronics, physical channel, network components and functions, networks, services, and cross-layer and cross-infrastructure considerations. After reviewing the background on resilience concepts, definitions, and approaches, we introduce the proposed resilience-by-design (RBD) concept for 6G communication networks. We further elaborate on the proposed RBD concept along with selected 6G use-cases and present various open problems for future research on 6G resilience.
... SCC-SVM computes a decision function f which encompasses the majority of the training data [Senigagliesi et al. (2020); Abdrabou and Gulliver (2022c); Abdrabou and Gulliver, 2022a; Abdrabou and Gulliver, 2023]. First, the following optimization problem is solved (Hoang et al., 2021); (Schölkopf et al., 2001): ...
... The decision function used to test a new sample t is expressed as follows (Senigagliesi et al. 2020); (Hoang et al. 2021): ...
Multiple-input multiple-output (MIMO) technology is employed to improve the reliability and capacity of wireless communication systems. However, the wireless communication environment creates vulnerabilities to spoofing attacks. Furthermore, the authentication challenges posed by the heterogeneous characteristics of wireless applications increase as diverse technologies facilitate the growing number of Internet of Things (IoT) devices. To address these challenges, adaptive physical-layer authentication (PLA) leveraging the inherent antenna diversity in MIMO systems is examined, and an information-theoretic perspective on PLA in MIMO systems is given. The real and imaginary components of the received reference signals are used as attributes with a single-class classification support vector machine (SCC-SVM). It is shown that the authentication performance improves with the number of antennas, and the proposed scheme provides robust authentication.
... This potential encompasses scenarios where individuals engage with secure data, such as banking details, through Post-Quantum Cryptography (PQC) techniques while routine browsing activities continue along the conventional route. This dynamic underscores the value of our hybrid network model, offering a framework that balances enhanced security with pragmatic functionality [15][16][17][18][19][20][21][22][23][24][25][26]. ...
This paper presents a novel hybrid communication policy developed using Hybrid Universal Network Coding Cryptosystem (HUNCC), which can perform post-quantum cryptography at a high information rate. This hybrid scheme (HUNCC) is based on the notion of individual secrecy and computational complexity, where we assume that if the eavesdropper has access to a small part of the communication link (ciphertext) between the sender and receiver, individual secrecy will ensure secure communication. However, If the eavesdropper can access the full link (ciphertext), then computational complexity can guarantee post-quantum security. We extend our study by applying fuzzy logic to HUNCC, helping us gain more insights. Specifically, we propose a novel Adaptive Neuro Fuzzy Inference System that provides a security metric from the input attributes, namely the physical layer (PHY) security attribute and cooperative sensing (CS) security attribute obtained from trusted sources. We assume such attributes are available for the ANFIS to evaluate a security metric that will decide on whether (i). to implement the cryptosystem over a single link in a multi-link system (HUNCC) or (ii). to completely use the notion of individual secrecy alone to encode the system, provided the output from ANFIS guarantees good security. This method can help switch between classical and quantum-secure communication, improving the effective throughput. Using HUNCC with a modified McEliece Cryptosystem that uses Hamming code, we obtain an information rate of 0.9507 bits, illustrating the increase in throughput obtained using the modified HUNCC model when compared to existing PQC techniques. Furthermore, we introduce a novel concept aimed at achieving even higher information rates. This approach relies on the security metric derived from ANFIS and involves dynamic switching between quantum and classical communication, guided by security risk factors. As a result, we achieve an information rate of up to 0.98 bits.
... Note that the position of Eve is often not known in practice as she tries to hide her presence from Alice. To deal with this issue, a promising approach is to identify the presence of Eve through CSI-based eavesdropper detection methods [54]. Therefore, our future work aims at joint adaptive modulation and precoding designs for such a scenario. ...
There has been an increasing interest in physical layer security (PLS), which, compared with conventional cryptography, offers a unique approach to guaranteeing information confidentiality against eavesdroppers. In this paper, we study a joint design of adaptive M-ary pulse amplitude modulation (PAM) and precoding, which aims to optimize wiretap visible-light channels’ secrecy capacity and bit error rate (BER) performances. The proposed design is motivated by higher-order modulation, which results in better secrecy capacity at the expense of a higher BER. On the other hand, a proper precoding design, which can manipulate the received signal quality at the legitimate user and the eavesdropper, can also enhance secrecy performance and influence the BER. A reward function that considers the secrecy capacity and the BERs of the legitimate user’s (Bob) and the eavesdropper’s (Eve) channels is introduced and maximized. Due to the non-linearity and complexity of the reward function, it is challenging to solve the optical design using classical optimization techniques. Therefore, reinforcement learning-based designs using Q-learning and Deep Q-learning are proposed to maximize the reward function. Simulation results verify that compared with the baseline designs, the proposed joint designs achieve better reward values while maintaining the BER of Bob’s channel (Eve’s channel) well below (above) the pre-FEC (forward error correction) BER threshold.
... In [79], researchers have developed an IDS architecture to monitor and detect lethal attacks such as price manipulation attacks, DoS attacks with detection rate of more than 95% and false positive rate is below 5% using a cumulative sum algorithm in smart grid. In [96], the authors have proposed an SVM algorithm to detect active eavesdropping attacks with detection probability of 95% using artificial training data in the wireless communication channel. From the presented work, adding more hidden features to the proposed algorithms can improve detection performance. ...
... Not only FDIA, eavesdropping attack also one of the cyber security vulnerable attacks in smart communication system. Researchers developed a deep learning architecture [94], SVM [96], decomposition form of the system matrices [26], dual denoising auto-encoder based encryptor [82] and a certificate-less signcryption [114] to analyse impact and detect DoS, eavesdropping attacks. Furthermore, researchers utilised a zero-knowledge proofs & the pailiers crypto system [102], as well as a blockchain & homomorphic encryption based aggregation architecture [139], to minimise smart meter data manipulation attacks. ...
Continuous communication and information technology advancements facilitate the modernization of the conventional energy grid into an integrated platform. Internet-of-Things (IoT) incorporates power systems, particularly smart grid features and the delivery of new services from the utility side to the end user over a two-way communication channel. However, severe security vulnerabilities have been created due to over-dependency on IoT based communication systems. In addition, critical information exchange between any two entities or devices is always an appealing target for cyber-attackers, especially with financial interest motive by damaging integrity, confidentiality and authenticity in a communication channel. Maintaining data security and preserving privacy in between two entities during the transmission or any data distribution are essential. The potential attacks and impacts of those attacks need to be investigated to develop an effective cyber security infrastructure. Thus, considerable researchers focused on detection and mitigation of these vulnerable cyber-attacks using advanced computation tools. This review article thoroughly investigated possible ways to address cyber security challenges such as smart meter security, end-users privacy, electricity theft cyber-attacks using blockchain and cryptography against communication attacks in smart grid. The operational impacts of cyber-attacks on power system security, as well as the economic impact on deregulated energy markets, have been extensively explored. In addition, the robustness of security features and cryptographic methods against various cyber-attacks is investigated to suggest unexplored cyber-attacks for future scope. Specially, the study of real-world cyber security events, case studies, new findings and new scopes in diverse power industries are carried out. More than 135 research articles has been examined for this review article. This paper mainly concentrates on distribution-side cyber-attacks with impact analysis, detection and protection techniques.
... 1 To obtain the channel state information (CSI) of the eavesdropper, several methods can be deployed, e.g., the energy ratio detectors, pilot signals, and support vector machines (SVM), etc. [20][21][22]. ...
The performance of the satellite-terrestrial network with Fountain codes (FCs) is conducted in the present work. More precisely, the air-to-ground link is modeled according to the shadow-Rician distribution to capture the strong light-of-sight (LOS) path as well as the impact of the shadowing. As a result, we employ the directional beamforming at both the satellite and relay to mitigate such an ultra-long transmission distance. We investigate the trade-off between the reliability and security aspects. Particularly, we derive the outage probability (OP) and intercept probability (IP) in the closed-form expressions. To further facilitate the security of the considered networks, the friendly jamming scheme is deployed as well. Finally, simulation results based on the Monte-Carlo method are given to corroborate the exactness of the developed mathematical framework and to identify key parameters such as antenna gain, and transmit power that have a big impact on the considered networks.
... In a cognitive eavesdropping environment, Reference [22] adopted distributed machine learning algorithms are used to optimize the allocation ratio of secondary device resources to ensure the quality of service for users with higher task priorities. The author of [23] using the relationship between transmitted and received signals considering the transmission process to build a dataset and using SVM algorithm to classify eavesdropping and legitimate signals, but the detection accuracy of binary classification is not very high. Reference [24] utilized a lightweight network composed of BP neural network, auto regressive integral moving average model, and SVM to achieve intrusion detection and recognition. ...
... Therefore, this article mainly addresses the issue of active eavesdropping detection in the wireless access process of general wireless systems. In order to enhance the performance of eavesdropping detection as well as the accuracy of signal classification, we build on the idea of [23,25] to generate test data from wireless signals, by using statistical knowledge of channel state information (CSI) to create a wireless signal dataset framework, and then artificial training data is created to input the data into ML and BP models. According to the characteristics of the dataset, a BP neural network model based on deep learning architecture has been proposed. ...
... According to the spirit of the dataset framework cited in [23], the idea of using the correlation between the signal transmitted and the signal received to consider the transmission process is introduced into the representation learning of wireless signal features. When user k sends a message requesting communication to the AP, E will steal its message and imitate k while transmitting it to the AP. ...
Considering the variety of Internet of Things (IoT) device types and access methods, it remains necessary to address the security challenges we currently encounter. Physical layer security (PLS) can offer streamlined security solutions for the next generation of IoT networks. Presently, we are witnessing the application of intelligent technologies including machine learning (ML) and artificial intelligence (AI) for precise prevention or detection of security breaches. Active eavesdropping detection is a physical layer security-based method that can differentiate wireless signals between wireless devices through feature classification. However, the operation of numerous IoT devices operate in environments characterized by low signal-to-noise ratios (SNR), and active eavesdropping attack detection during communication is rarely studied. We assume that the wireless system comprising an access point (AP), K authorized users and a proactive eavesdropper (E), following the framework of transforming wireless signals at AP into organized datasets that this article proposes a BP neural network model based on deep learning as a classifier to distinguish eavesdropping and non-eavesdropping attack signals. By conducting experiments under SNRs, the numerical results show that the proposed model has stronger robustness and detection accuracy can significantly improve the up to 19.58% compared with the reference approach, which show the superiority of our proposed method.
... This scheme employs a one-class classification support vector machine (OCC-SVM) and the results obtained show that the probability of missed detection improves with the number of subcarriers, but the probability of false alarm increases slightly. In [26], PLA was proposed which uses the mean and ratio of the received signals as features. This scheme employs a twoclass classification support vector machine (TCC-SVM) and a OCC-SVM. ...
... OCC-SVM computes a decision function f which encloses most of the training data [25], [26], [41]. A test sample t is accepted if f (t) > 0 which indicates it is within the authentication boundary. ...
... A test sample t is accepted if f (t) > 0 which indicates it is within the authentication boundary. First, the following optimization problem is solved [26], [39] min w,s,ρ ...
Internet of things (IoT) devices have become ubiquitous due to the prevalence of the internet. However, the open nature of wireless networks makes them susceptible to spoofing attacks. Moreover, their heterogeneous characteristics create authentication challenges which are increasing due to the tremendous growth in the number and variety of devices. Physical layer authentication (PLA) provides a solution by utilizing the unique characteristics of wireless channels to aid upper layer authentication (ULA). In this paper, an adaptive physical layer authentication scheme is proposed which exploits the antenna diversity inherent in multi-input-multi-output (MIMO) systems. This scheme employs a one-class classification support vector machine (OCC-SVM) with the magnitude and real and imaginary parts of the received signals as features. Results are presented which show that this scheme provides robust authentication. The authentication performance is evaluated considering two majority voting schemes for IoT applications.
... In this section, we evaluate the performance of the proposed authentication scheme in solving the device authentication problem. We plot the performance of three physical-channelbased authentication benchmark solutions: using binary hypothesis testing (BHT) [21], using machine learning-based SVM [50], and using deep neural network-based (NN) detection [51]. For these three benchmark solutions, the core architectures are borrowed from the respective works but their input configurations have been adjusted to our system model for a fair comparison. ...
Physical-layer authentication is a popular alternative to the conventional key-based authentication for internet of things (IoT) devices due to their limited computational capacity and battery power. However, this approach has limitations due to poor robustness under channel fluctuations, reconciliation overhead, and no clear safeguard distance to ensure the secrecy of the generated authentication keys. In this regard, we propose a novel, secure, and lightweight continuous authentication scheme for IoT device authentication. Our scheme utilizes the inherent properties of the IoT devices’ transmission model as its source for seed generation and device authentication. Specifically, our proposed scheme provides continuous authentication by checking the access time slots and spreading sequences of the IoT devices instead of repeatedly generating and verifying shared keys. Due to this, access to a coherent key is not required in our proposed scheme, resulting in the concealment of the seed information from attackers. Our proposed authentication scheme for IoT devices demonstrates improved performance compared to the benchmark schemes relying on physical channels. Our empirical results find a near threefold decrease in the misdetection rate of illegitimate devices and close to zero false alarm rate in various system settings with varied numbers of active devices up to 200 and signal-to-noise ratio from 0 dB to 25 dB. Our proposed authentication scheme also has a lower computational complexity of at least half the computational cost of the benchmark schemes based on support vector machine and binary hypothesis testing in our studies. This further corroborates the practicality of our scheme for IoT deployments.
... In the age of the Internet of Things, besides coverage and capacity improvements, security and reliability enhancements of wireless communication systems are the key requirements, especially in the fifth and beyond generations (5G and B5G) of wireless systems [1,2]. For the security requirements of the 5G and B5G wireless systems, physical layer security (PLS) has been proposed [3]. Unlike classical cryptographic algorithms, PLS utilizes the random nature of wireless channels for information security. ...
... Unlike classical cryptographic algorithms, PLS utilizes the random nature of wireless channels for information security. Consequently, the PLS can provide secrecy performance without depending on the computation resources of wireless devices [3,4]. As a result, the PLS is now widely considered and applied to enhance information security in 5G and B5G wireless systems [5][6][7]. ...
For the first time, this work employs analytic solutions to study static bending, as well as free and forced vibrations of organic nanobeams, including the impact of temperature. Calculation formulas are developed on the basis of the third-order shear strain theory of thickness. These formulas also account for the influence of the size effect by using nonlocal parameters. In contrast to the findings of earlier research on nanobeams, the nonlocal parameter in this investigation fluctuates with beam thickness. In addition to this, the viscous drag parameter of the beam is taken into consideration, which further complicates the calculation method, but this is also the new point of this work. The equation is developed using the potential work principle, and the Navier form solution is used to solve the resulting equilibrium equations. Nanobeams' natural frequency and static displacement have both real and complicated components due to the involvement of the drag parameter. The research also includes some numerical calculation findings for elucidating the impact of temperature and nonlocal parameters on the static bending response and free and forced vibration of organic nanobeams.
