Jammer Detection based on Artificial Neural Networks

Gecgel, Selen; Goztepe, Caner; Kurt, Güneş Karabulut

doi:10.1145/3324921.3328788

Cited by 39 publications

(31 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been studied to secure wireless communications, such as authenticating signals [37]- [39], detecting and classifying jammers of different types [40]- [42], and controlling communications to mitigate jamming effects [32], [40]. As cognitive radio capabilities are integrated into wireless communications, adversaries such as jammers become smarter, as well [40], [43].…”

Section: Related Workmentioning

confidence: 99%

Generative Adversarial Network in the Air: Deep Adversarial Learning for Wireless Signal Spoofing

Shi

Davaslıoğlu

Sagduyu

2021

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

The spoofing attack is critical to bypass physicallayer signal authentication. This paper presents a deep learningbased spoofing attack to generate synthetic wireless signals that cannot be statistically distinguished from intended transmissions. The adversary is modeled as a pair of a transmitter and a receiver that build the generator and discriminator of the generative adversarial network, respectively, by playing a minimax game over the air. The adversary transmitter trains a deep neural network to generate the best spoofing signals and fool the best defense trained as another deep neural network at the adversary receiver. Each node (defender or adversary) may have multiple transmitter or receiver antennas. Signals are spoofed by jointly capturing waveform, channel, and radio hardware effects that are inherent to wireless signals under attack. Compared with spoofing attacks using random or replayed signals, the proposed attack increases the probability of misclassifying spoofing signals as intended signals for different network topology and mobility patterns. The adversary transmitter can increase the spoofing attack success by using multiple antennas, while the attack success decreases when the defender receiver uses multiple antennas. For practical deployment, the attack implementation on embedded platforms demonstrates the low latency of generating or classifying spoofing signals. Index Terms-Adversarial machine learning, deep learning, generative adversarial network (GAN), spoofing attack.

show abstract

Section: Related Workmentioning

confidence: 99%

Generative Adversarial Network in the Air: Deep Adversarial Learning for Wireless Signal Spoofing

Shi

Davaslıoğlu

Sagduyu

2021

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…al, have proposed a CNN-based strategy named RFI-Net to detect interference in a five-hundred-meter Aperture Spherical radio Tele-scope (FAST) [14], that can outperform other techniques such as the U-Net model based on a CNN architecture, k-nearest neighbors (KNN) algorithms, as well as Sum-Threshold. In [15], two DL-based strategies are used for jamming attack detection, namely deep convolutional neural networks (DCNN) and deep recurrent neural networks (DRNN). In this research, two different jamming attacks, namely, classical wide-band barrage jamming and reference signal jamming have been analyzed [15].…”

Section: Related Workmentioning

confidence: 99%

“…In this research, two different jamming attacks, namely, classical wide-band barrage jamming and reference signal jamming have been analyzed [15]. The results show that the classification accuracy reaches up to 86.1% under a realistic test environment [15]. In [16] three methods including a Convolutional Long Short-term Deep Neural Network (CLDNN), a Long Short-Term Memory neural network (LSTM), and a deep Residual Network (ResNet) have been proposed to recognize ten different modulation types.…”

Section: Related Workmentioning

confidence: 99%

An Efficient Radio Frequency Interference Recognition Using End-to-end Transfer Learning

Ujan¹,

Navidi²,

Landry³

2020

Preprint

View full text Add to dashboard Cite

Radio Frequency Interference (RFI) detection and characterization play a critical role to in ensuring the security of all wireless communication networks. Advances in Machine Learning (ML) have led to the deployment of many robust techniques dealing with various types of RFI. To sidestep an unavoidable complicated feature extraction step in ML, this paper proposes an efficient end-to-end method using the latest advances in deep learning to extract the appropriate features of the RFI signal. Moreover, this study utilizes the benefits of transfer learning to determine both the type of received RFI signals and their modulation types. To this end, the scalogram of the received signals is used as the input of the pre-trained convolutional neural networks (CNN), followed by a fully-connected classifier. This study considers a digital video stream as the signal of interest (SoI), transmitted in a real-time satellite-to-ground communication using DVB-S2 standards. To create the RFI dataset, the SoI is combined with three well-known jammers namely, continuous-wave interference (CWI), multi- continuous-wave interference (MCWI), and chirp interference (CI). This study investigated four well-known pre-trained CNN architectures, namely, AlexNet, VGG-16, GoogleNet, and ResNet-18, for the feature extraction to recognize the visual RFI patterns directly from pixel images with minimal preprocessing. Moreover, the robustness of the proposed classifiers is evaluated by the data generated at different signal to noise ratios (SNR).

show abstract

“…Moreover, they present different intentional JI with their respective targets, and conclude that a more complex jamming is likely to become a bigger threat due to increase in the sophistication of wireless systems. In [21], the authors investigate the jammer detection along with its types using different neural network approaches in an OFDMA-based signaling scenario. They show that their proposed approach can detect and classify the jamming attacks with 85% accuracy.…”

Section: Related Workmentioning

confidence: 99%

“…1. In [14,[21][22][23][24][25], different jamming techniques with their detection and mitigation methods are investigated in different networks. However, these studies lack the analysis of both ICI and JI in HetNets along with RFA.…”

Section: Approach and Contributionsmentioning

confidence: 99%

Proactive Uplink Interference Mitigation in HetNets Stressed by Uniformly Distributed Wideband Jammers

Abbas

Haroon

et al. 2019

Electronics

View full text Add to dashboard Cite

In heterogeneous cellular networks (HetNets), densification of small base stations (SBSs) in the macro base station (MBS) coverage region leads to improved network coverage and capacity. However, this improvement is at the cost of inter-cell interference (ICI) due to the high MBS transmit power. The situation deteriorates further when uniformly deployed wideband jammers (WBJs) to initiate distributed denial-of-service (DDoS) attacks are present. With sufficient knowledge about the network parameters, WBJs produce substantial jammer interference (JI) by transmitting unwanted energy in the legitimate band. Such jamming attacks can cause significant JI in the UL communications of MBS edge users (M-EUs) due to i) low uplink (UL) transmit power of user equipment (UE) and ii) longer distances of M-EUs. As a result of ICI and JI, M-EUs are severely affected and go off the coverage due to a low received signal-to-interference ratio (SIR). Hence, to mitigate both ICI and JI, we use a proactive resource allocation scheme known as reverse frequency allocation (RFA). The results indicate that although ICI and JI significantly degrade network performance, RFA employment leads to improved SIR due to effective ICI and JI mitigation.

show abstract

Jammer Detection based on Artificial Neural Networks

Cited by 39 publications

References 9 publications

Generative Adversarial Network in the Air: Deep Adversarial Learning for Wireless Signal Spoofing

Generative Adversarial Network in the Air: Deep Adversarial Learning for Wireless Signal Spoofing

An Efficient Radio Frequency Interference Recognition Using End-to-end Transfer Learning

Proactive Uplink Interference Mitigation in HetNets Stressed by Uniformly Distributed Wideband Jammers

Contact Info

Product

Resources

About