Primary User Emulation Attack Detection Research Articles

A Reliable Spectrum Sensing Method Based on Deep Learning for Primary User Emulation Attack Detection in Cognitive Radio Network

A Reliable Spectrum Sensing Method Based on Deep Learning for Primary User Emulation Attack Detection in Cognitive Radio Network

PUE Attack Detection by Using DNN and Entropy in Cooperative Mobile Cognitive Radio Networks

The primary user emulation (PUE) attack is one of the strongest attacks in mobile cognitive radio networks (MCRN) because the primary users (PU) and secondary users (SU) are unable to communicate if a malicious user (MU) is present. In the literature, some techniques are used to detect the attack. However, those techniques do not explore the cooperative detection of PUE attacks using deep neural networks (DNN) in one MCRN network and with experimental results on software-defined radio (SDR). In this paper, we design and implement a PUE attack in an MCRN, including a countermeasure based on the entropy of the signals, DNN, and cooperative spectrum sensing (CSS) to detect the attacks. A blacklist is included in the fusion center (FC) to record the data of the MU. The scenarios are simulated and implemented on the SDR testbed. Results show that this solution increases the probability of detection (PD) by 20% for lower signal noise ratio (SNR) values, allowing the detection of the PUE attack and recording the data for future reference by the attacker, sharing the data for all the SU.

Signal Processing-based Model for Primary User Emulation Attacks Detection in Cognitive Radio Networks

Cognitive Radio Networks (CRNs) have been conceived to improve the efficiency of accessing the spectrum. However, these networks are prone to various kinds of attacks and failures that can compromise the security and performance of their users. One of the notable malicious attacks in cognitive radio networks is the Primary User Emulation (PUE) attack, which results in underutilization and unavailability of the spectrum and low operational efficiency of the network. This study developed an improved technique for detecting PUE attacks in cognitive radio networks and further addressed the characteristics of sparsely populated cognitive radio networks and the mobility of the primary users. A hybrid signal processing-based model was developed using the free space path loss and additive Gaussian noise models. The free space path loss model was used to detect the position of the transmitter, while the additive Gaussian noise model was used to analyze the signal transmitted, i.e., energy detection in the spectrum at the detected location. The proposed model was benchmarked with an existing model using the number of secondary users and the velocity of the transmitter as performance parameters. The simulation results show that the proposed model has improved accuracy in detecting primary user emulation attacks. It was concluded that the proposed hybrid model with respect to the number of secondary users and the velocity of the transmitter can be used for primary user emulation attack detection in cognitive radio networks.

Investigations on detection and prevention of primary user emulation attack in cognitive radio networks using extreme machine learning algorithm

Cognitive radio is a competent technology which resolves the spectrum scarcity crisis in a network by allocating free spectrum dynamically and establishes coexistence between the users of the network, without interfering with the incumbent transmission. Primary user emulation attack (PUEA) is one of the major threats to the spectrum sensing performance that decreases the spectrum access probability of the unlicensed users of the network. In this paper Detection and prevention of PUEA is realized proficiently using Time-Distance with signal Strength Evaluation (TDSE) and Extreme Machine Learning (EML) algorithm. TDSE implementation makes it feasible to identify the malicious PUE attacker under mobile user stipulation and EML algorithm provides a swift comparative decision regarding the malicious attack. The technique is also proven to improve the sensing ability, energy efficiency and brings down the overall delay of the system, illustrating a considerable improvement in the overall network performance and spectrum utilization in a cognitive radio network.

Detection and Defense of PUEA in Cognitive Radio Network

In wireless communication, there is an enormous increase in the number of users which results in spectrum shortage. This can be defeated through dynamic spectrum access scheme and cognitive radio is the best solution to achieve this. A cognitive radio (CR) is programmable, configurable and can dynamically use the spectrum in the wireless environment. One of the important tasks of CR is to perform spectrum sensing. Sensing done on spectrum facilitates the cognitive radio user to find the unoccupied area of the spectrum. This CR is prone to many attacks in the wireless environment like primary user emulation attack (PUEA), denial of service attack, replay attack, etc. Among them, the most important attack is PUEA. When a user mimics the primary user and acquires priority over other users to access the spectrum then it is termed as PUEA. In this work, PUEA detection and its defense techniques have been modeled to avoid the degradation of spectrum. To detect the malicious users feature detection-based sensing with double threshold has been proposed. If the detected signal falls above the upper threshold or below the lower threshold then it is considered as primary user signal, whereas if the signal falls in between the thresholds then that signal is identified as malicious user signal. The detection of PUEA cannot be accurate due to factors like false alarm and miss detection. Hence, a game model has been designed for the legitimate nodes to reach strategic defense decisions in the presence of multiple attackers. Based on the actions of the players, the defenders’ payoff is determined to obtain optimal defense decisions.

A Multi-Objective Particle Swarm Optimization Based Algorithm for Primary User Emulation Attack Detection

The cognitive radio network (CRN) has been proposed to overcome the spectrum scarcity and the massive demand on the radio frequencies through efficient utilization and smart management of the free channels. Using a spectrum sensing process, the secondary users (SUs) share the spectrum of the primary users (PUs) without causing any interference to these latter. One of the main threats affecting the channel utilization in CRN is the primary user emulation (PUE) attack. The PUE attack utilizes a sophisticated technique to craft the same signal of a legitimate PU to gain unauthorized access to the unused channels, forcing the SUs to immediately free up vacant spectrum space, resulting in a denial of service (DoS), degradation of service, and causing a noticeable impact on CRN performance. To circumvent this attack, the anchor nodes must accurately estimate the coordinates of the PU signal source. In the literature, most of the localization of unknown signal source, in our case the PU/PUE, are based on the ranging schemes which measure the distance between the blind node and the anchors. Those anchors are aware of their location and situated in optimized positions to the signal source in order to permit an accurate PU/PUE position detection. The detection rate depends tightly on the distance separating the anchors to the signal source as well as the signal-to-noise ratio (SNR). In this paper, we demonstrate the impact of the distance on the detection error while highlighting the particle swarm optimization’s (PSO) advantage in optimizing the anchors positioning. Furthermore, we illustrate the SNR impact on the probability of detection, particularly in the situation of low SNR and the attacker in the vicinity to a real PU. The main contribution in this work is the proposition of an approach with the aim of protecting an area containing more than a single PU with a limited number of anchor nodes while providing a higher detection rate to stop any eventual PUE attack. This approach is based on a multi-objective particle swarm optimization (MOPSO) algorithm for PU/PUE position detection. It minimizes concurrently the probability of detection error related to the received signal strength (RSS)/trilateration and the SNR, with the main objective of finding all optimized positions for the mobile anchor nodes and obtains the most accurate PUE attack detection.

Primary user emulation attack mitigation using neural network

The spectrum sensing scheme suffers from a physical layer attack of Primary User Emulation Attack (PUEA). The resolution is to mitigate the cognitive radio user from the PUEA under the physical layer. Detecting the PUEA attack in real-time is a challenging one. The traditional Location-based PUEA detection requires the primary user's location knowledge, which may not be possible practically. This research focuses on developing a reliable spectrum sensing mechanism in the presence of PUEA attack and rapid change in the wireless channel. This reliable spectrum sensing framework is developed using the neural network-based PUEA detector excluding the location information. The Software-Defined Radio (SDR) called Universal Software Radio Peripheral (USRP) 2943R is used to implement the proposed mechanism for analyzing performance in real-time. The real-time experimental results show that PUEA detection can be achieved with 97% accuracy.

Semi-supervised machine learning for primary user emulation attack detection and prevention through core-based analytics for cognitive radio networks

Cognitive radio networks are software controlled radios with the ability to allocate and reallocate spectrum depending upon the demand. Although they promise an extremely optimal use of the spectrum, they also bring in the challenges of misuse and attacks. Selfish attacks among other attacks are the most challenging, in which a secondary user or an unauthorized user with unlicensed spectrum pretends to be a primary user by altering the signal characteristics. Proposed methods leverage advancement to efficiently detect and prevent primary user emulation future attack in cognitive radio using machine language techniques. In this paper novel method is proposed to leverage unique methodology which can efficiently handle during various dynamic changes includes varying bandwidth, signature changes etc… performing learning and classification at edge nodes followed by core nodes using deep learning convolution network. The proposed method is compared with that of two other state-of-art machine learning-based attack detection protocols and has found to significantly reduce the false alarm to secondary network, at the same time improve the overall detection accuracy at the primary network.

A decision‐making approach for detecting the primary user emulation attack in cognitive radio networks

SummaryCognitive radio network (CRN) is a promising technology, which enables secondary users to use the free spectrum channels without causing detrimental interference with the primary user (PU). Nevertheless, CRN is subject to numerous cyber attacks that have a negative impact on its performance. Among the CRN attacks, the primary user emulation (PUE) attack is known to be one of the malicious attacks threatening CRN security. Several attacks detection techniques, based on attacker localization, have been investigated in the literature. These techniques include the trilateration, received signal strength indication (RSSI), and network coding approach as well. However, most of these techniques do not consider the uncertainty related to CRN, which can be modeled by a cost function defined as a weighted sum of conditional probabilities. In this paper, a localization technique, relied on a trilateration computation and a Bayesian model, is proposed for PUE position detection purpose under uncertainty conditions assumption. Particularly, the estimation of PUE position is performed through trilateration method based on RSSI at the anchor nodes for the signal coming from either PU or PUE, whereas, the Bayesian decision model, based on a cost function, is involved to check the PU legitimacy. The simulation results show that the decision‐making approach "Security, productivity, Balancing" influences directly the zone of the PUE attack detection.

Joint cooperative spectrum sensing and primary user emulation attack detection in cognitive radio networks using fuzzy conditional entropy maximization

AbstractCooperative spectrum sensing (CSS) in cognitive radio system shows improved performance on spectrum sensing but, at the same time, faces a common threat called primary user emulation attack (PUEA) that impersonates the primary user (PU). This work explores joint PU and PUEA detection on CSS as a multiclass hypothesis using fuzzy conditional entropy maximization. To meet the goal, a multithreshold approach is suggested using a constrained differential evolution algorithm search to determine an optimal set of fuzzy function parameters, which maximizes the conditional entropy on the energy values. The proposed work also investigates the performance of CSS in presence of a group of malicious users (as PUEA), which generates signals and directly sends the same to the fusion center. Numerical results through simulation illustrate the efficacy of the proposed scheme in terms of both reliable PU detection in presence or absence of PUEA/malicious user and separate detection of falsifying PU and energy consumption in CSS. Simulation results show that the proposed scheme offers ∼17.54% and ∼39.39% higher detection probability of PU over the existing works in presence of PUEA.

Trust Establishment in Chaotic Cognitive Environment to Improve Attack Detection Accuracy Under Primary User Emulation

In this paper, we propose a novel algorithm for primary user emulation attack detection and removal in cognitive radio networks, which are driven by chaotic tag-based sequencing for communication. Our proposed approach demonstrates the use of the look-up table-based challenge sequences which are monitored by the cognitive base station and act as the first line of defense against any primary user emulation attacker. This ensures that almost all of the attackers are suppressed, and for the remaining attackers if any, we use a tag-based chaotic communication system, wherein each of the requests from secondary users is sent like a chaotic noise sequence on the channel, and the receiving entity decodes this sequence in order to get the signal communicated by an authorized transmitter. If there is any communication by an attacker, then it is detected immediately, as none of the receiving entities can decode the signals sent by these unwanted attacker nodes. This ensures that our system guarantees greater than 99% detection and identification of attackers in primary user emulation attacks.

Defence against PUE attacks in ad hoc cognitive radio networks: a mean field game approach

Cognitive Radio (CR) is an emerging and promising communication technology geared towards improving vacant licensed band utilization, intended for unlicensed users. Security of Cognitive Radio Networks (CRN) is a highly challenging domain. At present, plenty of efforts are in place for defining new paradigms, techniques and technologies to secure radio spectrum. In a distributed cognitive radio ad-hoc network, despite dynamically changing topologies, lack of central administration, bandwidth-constraints and shared wireless connections, the nodes are capable of sensing the spectrum and selecting the appropriate channels for communication. These unique characteristics unlock new paths for attackers. Standard security techniques are not an effective shield against attacks on these networks e.g. Primary User Emulation (PUE) attacks. The paper presents a novel PUE attack detection technique based on energy detection and location verification. Next, a game model and a mean field game approach are introduced for the legitimate nodes of CRN to reach strategic defence decisions in the presence of multiple attackers. Simulation of the proposed technique shows a detection accuracy of $${89\%}$$ when the probability of false alarm is 0.09. This makes it 1.32 times more accurate than compared work. Furthermore, the proposed framework for defence is state considerate in making decisions.

Coordination Without Collaboration in Imperfect Games: The Primary User Emulation Attack Example

In cognitive radio networks, an adversary transmits signals with characteristics that emulate those of primary users to prevent secondary users from transmitting. Such an attack is called a primary user emulation (PUE) attack. In this paper, a game theoretical framework is proposed to study the primary user emulation attack (PUEA) on cognitive radio nodes as a game of imperfect information between the secondary users (SUs), who do not exchange game information between them against the adversaries generating the PUEA and to define optimal strategies with minor computational demands. When the SU challenges the PU emulator successfully, updating the information on a cloud-based database enables the rest of the network to know the identity of PUE. As the game evolves, the grand coalition of the secondary users acts as the one without collaboration against the PU emulator playing a winning strategy. The performance of the game for optimal strategies is equal to the performance of the collaborative methods for PUEA detection.

On detecting primary user emulation attack using channel impulse response in the cognitive radio network

Cognitive radio is an effective technology to alleviate the spectrum resource scarcity problem by opportunistically allocating the spare spectrum to unauthorized users. However, a serious denial-of-service (DoS) attack, named the ‘primary user emulation attack (PUEA)’, exists in the network to deteriorate the system performance. In this paper, we propose a PUEA detection method that exploits the radio channel information to detect the PUEA in the cognitive radio network. In the proposed method, the uniqueness of the channel impulse response (CIR) between the secondary user (SU) and the signal source is used to determine whether the received signal is transmitted by the primary user (PU) or the primary user emulator (PUE). The closed-form expressions for the false-alarm probability and the detection probability of the proposed PUEA detection method are derived. In addition, a modified subspace-based blind channel estimation method is presented to estimate the CIR, in order for the proposed PUEA detection method to work in the scenario where the SU has no prior knowledge about the structure and content of the PU signal. Numerical results show that the proposed PUEA detection method performs well although the difference in channel characteristics between the PU and PUE is small.

SVM based Two Level Authentication for Primary user Emulation Attack Detection

Background/Objectives: Cognitive radio network is the evolutionary network to solve the spectrum scarcity problem. Primary User Emulation Attack is a major security issue that cause to fail the dynamic spectrum access of the cognitive radio network. Methods/Statistical Analysis: This paper proposes two level verification of the primary user signal to enhance the security of the spectrum sensing under PUEA attack. Support Vector Machine is used in the two level verification for detector classify the received data in to a location boundary and higher order statics at second level. Findings: At first level using the location information of the primary user, the primary user signal is verified for its validity. The SVM is first trained to learn the Primary user Location and with the help of known location of the Primary user it can be verified. Then the trained SVM is used to find the location boundary of the user that transmitted the signal. If the signal boundary is within the primary used location boundary it is concluded that the signal is from the primary user; else it is from the PUEA attacker .After verifying in the first level on the second level higher order statics values are calculated then using that as the feature vector the SVM classifier is used to classify the received signal as two class: one from original primary user and other from the PUEA attacker. This two level verification of the primary user signal will be more accurate method of PUEA attack detection comparing to the single level schemes. Applications/Improvements:This two level verification scheme improves the accuracy from 82% at Linear SVM kernel to 100% and also from 77% at RBF SVM kernel to 100%.

Higher Order Statics based Primary User Emulation Attack Detection

Cognitive radio is one of the promising technique for dynamic spectrum sharing to solve the spectrum scarcity problem. Spectrum sensing is the key process in cognitive radio for the dynamic spectrum usage. But security in sensing is still in research issues .there are many security threads in cognitive radio but the primary user emulation attack is the predominant one which will not allow the dynamic spectrum sharing in effect. This primary emulation attack is the major drawbacks in energy detector based spectrum sensing. There are various methods to detect the emulation attack like RSSI based, location based etc. But the accuracy of detection is not good because of the uncertainty in the received power due to the random behavior of the channel condition. Most of those methods assume that primary users are stationary and channel variations are not significant. But in real time this assumption is not valid one .Here in this paper we propose higher order statics based primary user attack detection is proposed which can model the features of the primary user and primary user emulator attackers very well and we are able to detect the primary user emulation attack accurately. Here various fading channel scenarios like Rayleigh, rician and nagagammi is considered between the primary user and the attackers on that the performance of the detection of primary user emulation is analyzed.

Subband PUEA Detection and Mitigation in OFDM-Based Cognitive Radio Networks

This paper considers malicious user detection and energy harvesting in orthogonal frequency division multiplexing-based cognitive radio networks under primary user emulation attack (PUEA). The digital TV (DTV) model adopted is the second generation terrestrial digital television standard (DVB-T2). In this paper, first, we propose an efficient advanced encryption standard (AES)-based DTV scheme, where the existing reference sequence used to generate the P2 pilot symbols in the DVB-T2 frames is encrypted using the AES algorithm to facilitate accurate primary user and malicious user detection. With the proposed scheme, we can detect PUEA accurately over all subcarriers or subbands where the P2 symbols present. Second, we come up with an effective communication scheme for the secondary users (SUs) under PUEA by exploiting the energy harvesting techniques. Optimal power splitting is considered for sum-rate maximization. As the optimal solution relies on multidimensional exhaustive search, we propose an effective suboptimal solution with much lower computational complexity. It is observed that the sum-rate of the SU network can be improved significantly with the energy harvesting technique. Third, we evaluate the worst case PUEA interference in terms of minimizing the sum-rate for the SUs. We show that for practical systems, as channel state information among the SUs is not available to the malicious user, the worst jamming for the SUs is when the malicious user performs equal power allocation over all the white space subcarriers. Simulation results are provided to illustrate the proposed approaches.

Detecting Multi-ChannelWireless Microphone User Emulation Attacks in White Space with Noise

Cognitive radio networks (CRNs) are susceptible to primary user emulation (PUE) attacks. Conventional PUE attack detection approaches consider television broadcasting as the primary user. In this work, however, we study a special kind of PUE attack named wireless microphone user emulation (WMUE) att

Detection of PUE Attacks in Cognitive Radio Networks Based on Signal Activity Pattern

Promising to significantly improve spectrum utilization, cognitive radio networks (CRNs) have attracted a great attention in the literature. Nevertheless, a new security threat known as the primary user emulation (PUE) attack raises a great challenge to CRNs. The PUE attack is unique to CRNs and can cause severe denial of service (DoS) to CRNs. In this paper, we propose a novel PUE detection system, termed Signal activity Pattern Acquisition and Reconstruction System. Different from current solutions of PUE detection, the proposed system does not need any a priori knowledge of primary users (PUs), and has no limitation on the type of PUs that are applicable. It acquires the activity pattern of a signal through spectrum sensing, such as the ON and OFF periods of the signal. Then it reconstructs the observed signal activity pattern through a reconstruction model. By examining the reconstruction error, the proposed system can smartly distinguish a signal activity pattern of a PU from a signal activity pattern of an attacker. Numerical results show that the proposed system has excellent performance in detecting PUE attacks.

PUE attack detection in CWSNs using anomaly detection techniques

Cognitive wireless sensor network (CWSN) is a new paradigm, integrating cognitive features in traditional wireless sensor networks (WSNs) to mitigate important problems such as spectrum occupancy. Security in cognitive wireless sensor networks is an important problem since these kinds of networks manage critical applications and data. The specific constraints of WSN make the problem even more critical, and effective solutions have not yet been implemented. Primary user emulation (PUE) attack is the most studied specific attack deriving from new cognitive features. This work discusses a new approach, based on anomaly behavior detection and collaboration, to detect the primary user emulation attack in CWSN scenarios. Two non-parametric algorithms, suitable for low-resource networks like CWSNs, have been used in this work: the cumulative sum and data clustering algorithms. The comparison is based on some characteristics such as detection delay, learning time, scalability, resources, and scenario dependency. The algorithms have been tested using a cognitive simulator that provides important results in this area. Both algorithms have shown to be valid in order to detect PUE attacks, reaching a detection rate of 99% and less than 1% of false positives using collaboration.