Primary-User-Friendly Dynamic Spectrum Anti-Jamming Access: A GAN-Enhanced Deep Reinforcement Learning Approach

Han, Hao; Xu, Yifan; Zhu, Jianguo; Wen, Li; Chen, Xueqiang; Fang, Gui; Xu, Yuhua

doi:10.1109/lwc.2021.3125337

Cited by 15 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only effective with simple channel models Use GAN to learn the probability distribution functions of wireless channels, resulting in better channel response approximation [ from legitimate signals. Similarly, the authors in [90] and [82] aim to prevent jamming attacks as well as interference from secondary users in cognitive radio networks. They first highlight that conventional DL-based anti-jamming approaches give poor performance when spectrum data is not sufficient.…”

Section: Channel Equalizationmentioning

confidence: 99%

“…Incorporating an encoder network into the original GAN to reconstruct the spectrogram [94] Most detection methods cannot effectively detect spoofing jamming if spoofing signals are similar to authentic signals Design a GAN network that is trained on a large dataset of authentic satellite signals to accurately learn their distribution [103] Cannot effectively use to perform attacks Use GAN to construct synthetic RF signals that are similar to legitimate signals [95] Difficult to apply to the key generation in the physical layer Propose a key generation method based on GAN to extract features efficiently between legitimate nodes [104] Not effective in anomaly detection as GAI Use GAN to identify unrecognized patterns on the model outputs and associated sequenced metadata [90] Poor performance when spectrum data is not sufficient Use GAN to generate synthetic spectrum data that can help DRL to effectively learn and obtain the optimal dynamic spectrum anti-jamming access policy [92] Lack of labeled data Use GAN to learn the distribution of collected signals [86] Need attackers' information for training Use VAEs to extract valuable features of high-dimensional channel impulse responses for authentication GAN network to augment the training dataset of the classifier with adversarial samples generated from adversaries' GAN networks. Simulation results then show that by augmenting the training data with GAN the authors can effectively improve the classification accuracy under GAN-based adversarial attacks.…”

Section: Channel Equalizationmentioning

confidence: 99%

See 1 more Smart Citation

Effect of heavy metals on duckweed growth

Nguyen¹,

Hoang²,

Pham³

et al. 2022

CTUJS

View full text Add to dashboard Cite

In this study, three clones of the duckweed genus Lemna, collected from three different regions of Vietnam Binh Thuan Bac Giang and Ben Tre were used to evaluate the growth and development in a culture medium containing different concentrations of As3+, Cd2+, or Pb2+. During 14 days of incubation, the growth rate was determined daily by measuring the surface area of all plants of each sample. Experimental results show that the three Lemna clones could grow in nutrient medium contaminated by heavy metal at a concentration of 0.3-0.5 mg/L for As3+, 0.15-0.3 mg/L for Cd2+, and 0.15 mg/L for Pb2+. At these concentrations, the division rate of the treated clones was several times higher than that of the controls. The highest increase in the surface area was recorded for Lemna BTN (68.47 times higher when cultured in medium supplemented in 0.3 mg/L Pb2+ than under control conditions). The surface area of Lemna BTR cultured in a medium supplemented with 0.3 mg/L As3+ was 54.65 times higher than in medium without arsenic. The obtained results showed that Lemna BGG and Lemna BTR can tolerate arsenic and cadmium pollution while Lemna BTN tolerates lead pollution.

show abstract

Section: Channel Equalizationmentioning

confidence: 99%

Section: Channel Equalizationmentioning

confidence: 99%

Effect of heavy metals on duckweed growth

Nguyen¹,

Hoang²,

Pham³

et al. 2022

CTUJS

View full text Add to dashboard Cite

show abstract

“…In the virtual environment, a CDN is trained to learn the best spectrum access strategy. Finally, under the supervision of the skilled CDN, SU accesses the spectrum environment 48–50 . However, the data‐based strategy is more significant for learning the process through historical data monitoring in semiconductor industries to meet the higher power requirements related to the flow of data generated using different IoT and sensor‐related devices 51 .…”

Section: Literature Surveymentioning

confidence: 99%

“…Finally, under the supervision of the skilled CDN, SU accesses the spectrum environment. [48][49][50] However, the data-based strategy is more significant for learning the process through historical data monitoring in semiconductor industries to meet the higher power requirements related to the flow of data generated using different IoT and sensor-related devices. 51 Furthermore, the knowledge-based method frequently necessitates trained competence and domain knowledge to generate a suitable judgment based on the flawed data correlation structure.…”

Section: Literature Surveymentioning

confidence: 99%

To mitigate primary user emulation attack trajectory using cognitive single carrier frequency division multiple access approaches: Towards next generation green IoT

Mazumdar

Gohel

2023

Engineering Reports

View full text Add to dashboard Cite

The growing cognizance of spectrum scarcity has become a more significant concern in wireless radio communications. Due to the exponential growth of data transmission in intelligent wireless sensor networks, energy spectrum detection has become a promising solution for resolving spectrum shortages. Primary user emulation attack (PUEA) has been identified as a significant attack vector in the cognitive radio (CR) domain's physical layer. In comparison, the CR is a promising method to increase spectrum efficiency by allowing unlicensed secondary users (SUs) to access licensed frequency bands without interfering with approved primary users (PUs). The study's primary findings are the methodology for preventing PUEA using authentication tags, which are unique sequences. This research blends SC‐FDMA with CR to protect CR networks from PUEA attacks, a Latin square (LS) matrix tag generation system is proposed to mitigate the PUEA effect. The technology is meant to provide effective authentication and protection against malicious users. In a secured environment, the LS tag technique is utilized to track and estimate the PU. For example, the BER of both techniques is virtually identical between 0 and 4 dB, while the BER performance of the suggested LS tag generation improves with increasing signal‐to‐noise ratio (SNR). As a result, the suggested LS tag generation is less susceptible to PUEA. To diminish the influence of PUEA in CR networks, an efficient enlightening approach for making the future Green Cognitive Radio Wireless networks structure is proposed. The simulation results also demonstrate the resilience of the proposed CR spectrum sensing techniques for energy‐efficient knowledge at varying degrees to reduce the adverse effects of environmental technologies.

show abstract

“…With the continuous development of artificial intelligence technology, machine learning technology represented by reinforcement learning has also begun to be used in the field of communication anti-jamming [11,12]. A time-domain anti-pulse jamming algorithm (TDAA) based on reinforcement learning is proposed in [13]; this algorithm has a higher time utilization ratio and normalized throughput.…”

Section: Introductionmentioning

confidence: 99%

A Novel Anti-Jamming Decision-Making Algorithm Based on Knowledge Graph Technology

et al. 2022

View full text Add to dashboard Cite

Wireless communications are increasingly vulnerable to malicious jamming attacks due to the inherent openness and broadcast nature. In this regard, a novel anti-jamming scheme based on knowledge graph is proposed in this paper, where the knowledge graph which contains the prior knowledge of the commonly-used jamming patterns is utilized to make the fast anti-jamming decision with low complexity. Specifically, for the known jamming patterns, the anti-jamming strategy is directly extracted based on the search from the knowledge graph by using the sensing information. On the other hand, for the unknown jamming patterns, a time-frequency domain feature extraction method is first proposed to extract the jamming feature and match the jamming patterns in the knowledge graph. As such, multiple anti-jamming strategies can be obtained by the knowledge graph search. Finally, the optimal strategy can be achieved by the two communication decision criteria-based strategy fusion. The simulation results showed that the time-frequency domain feature extraction method can well extract the time-frequency domain feature of the jamming pattern, and the proposed algorithm has high decision accuracy and robustness.

show abstract

Primary-User-Friendly Dynamic Spectrum Anti-Jamming Access: A GAN-Enhanced Deep Reinforcement Learning Approach

Cited by 15 publications

References 13 publications

Effect of heavy metals on duckweed growth

Effect of heavy metals on duckweed growth

To mitigate primary user emulation attack trajectory using cognitive single carrier frequency division multiple access approaches: Towards next generation green IoT

A Novel Anti-Jamming Decision-Making Algorithm Based on Knowledge Graph Technology

Contact Info

Product

Resources

About