FaIR: Federated Incumbent Detection in CBRS Band

Troglia, Matthew; Melcher, Jordan; Zheng, Yao; Anthony, Dylan; Yang, Alvin; Yang, Tao

doi:10.1109/dyspan.2019.8935736

Cited by 16 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The existing ML-based works for database-assisted SS networks are mainly focused on the EZ adjustment [44], [45], ESC performance improvement [46], [47], and spectrum access coordination [48]- [51].…”

Section: B Database Assisted Ssmentioning

confidence: 99%

See 1 more Smart Citation

When Machine Learning Meets Spectrum Sharing Security: Methodologies and Challenges

Wang

Sun

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

The exponential growth of internet connected systems has generated numerous challenges, such as spectrum shortage issues, which require efficient spectrum sharing (SS) solutions. Complicated and dynamic SS systems can be exposed to different potential security and privacy issues, requiring protection mechanisms to be adaptive, reliable, and scalable. Machine learning (ML) based methods have frequently been proposed to address those issues. In this article, we provide a comprehensive survey of the recent development of ML based SS methods, the most critical security issues, and corresponding defense mechanisms. In particular, we elaborate the state-of-the-art methodologies for improving the performance of SS communication systems for various vital aspects, including ML based cognitive radio networks (CRNs), ML based database assisted SS networks, ML based LTE-U networks, ML based ambient backscatter networks, and other ML based SS solutions. We also present security issues from the physical layer and corresponding defending strategies based on ML algorithms, including Primary User Emulation (PUE) attacks, Spectrum Sensing Data Falsification (SSDF) attacks, jamming attacks, eavesdropping attacks, and privacy issues. Finally, extensive discussions on open challenges for ML based SS are also given. This comprehensive review is intended to provide the foundation for and facilitate future studies on exploring the potential of emerging ML for coping with increasingly complex SS and their security problems.

show abstract

Section: B Database Assisted Ssmentioning

confidence: 99%

“…An ML-based spectrum sensing system called Federated Incumbent Detection in CBRS (FaIR) was proposed in [46]. Federated learning (FL) was adopted for ESCs to collaborate and train a data-driven ML model for IU detection with minimal communication overhead.…”

Section: ) ML Based Ez Optimizationmentioning

confidence: 99%

When Machine Learning Meets Spectrum Sharing Security: Methodologies and Challenges

Wang

Sun

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…The National Telecommunications and Information Administration (NTIA) has published in [23] radar signal parameter bounds to facilitate a device's ESC performance. The literature from the past few years has only looked at radar detection in the CBRS band [24][25][26] which identifies whether a radar signal is present or not (binary classification). However, future ESC systems would require radar identification for comprehensive dynamic spectrum access such that the spectrum reallocation can be performed in a more informed manner.…”

Section: Case Study: Cbrs Radar Waveform Classificationmentioning

confidence: 99%

Deep neural network goes lighter: A case study of deep compression techniques on automatic RF modulation recognition for Beyond 5G networks

Jagannath¹,

Jagannath²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automatic RF modulation recognition is a primary signal intelligence (SIGINT) technique that serves as a physical layer authentication enabler and automated signal processing scheme for the beyond 5G and military networks. Most existing works rely on adopting deep neural network architectures to enable RF modulation recognition. The application of deep compression for the wireless domain, especially automatic RF modulation classification, is still in its infancy. Lightweight neural networks are key to sustain edge computation capability on resource-constrained platforms. In this letter, we provide an in-depth view of the state-of-the-art deep compression and acceleration techniques with an emphasis on edge deployment for beyond 5G networks. Finally, we present an extensive analysis of the representative acceleration approaches as a case study on automatic radar modulation classification and evaluate them in terms of the computational metrics.

show abstract

“…1 presents the system model which comprises of incumbents, PAL devices, and GAA devices. In this work, we consider that ESC sensors are deployed and exclusion zones are converted into protection zones [3], [21]. Let N denote the total number of real incumbents in the system.…”

Section: System Model a Snapshot Based Modelmentioning

confidence: 99%

Preserving Operation Frequency Privacy of Incumbents in CBRS

2022

View full text Add to dashboard Cite

Citizens Broadband Radio Service (CBRS) is a novel service band in the United States, spanning 3550 − 3700 MHz, recently opened for commercial cognitive operations. The CBRS has a three tier hierarchical architecture, wherein, the topmost tier users (also called as incumbents) include military radars. The second and third tier facilitate licensed and unlicensed access to the band, respectively. The privacy of incumbents has been a major concern and different schemes have been proposed in the literature to preserve privacy of their location and operation time. However, the privacy of operation frequency of incumbents has not been suitably addressed. The operation frequency of incumbent is vulnerable to inference attacks from the adversary. For instance, an adversary can deduce the operation frequency of incumbent if a compromised device is asked to switch to another channel. Therefore, in this paper, we propose probabilistic usage of dummy incumbents on a channel and analyse the operation frequency privacy of incumbents for snapshot and time based models in the three tier CBRS system. The optimum dummy generation probability is obtained for the snapshot and time based models, varying capabilities of the adversary, and different system parameters. Finally, we verify the proposed results through simulations.INDEX TERMS Citizens broadband radio service (CBRS), military radars, operation frequency privacy, preemptive resume priority queue, spectrum access system (SAS).

show abstract

FaIR: Federated Incumbent Detection in CBRS Band

Cited by 16 publications

References 10 publications

When Machine Learning Meets Spectrum Sharing Security: Methodologies and Challenges

When Machine Learning Meets Spectrum Sharing Security: Methodologies and Challenges

Deep neural network goes lighter: A case study of deep compression techniques on automatic RF modulation recognition for Beyond 5G networks

Preserving Operation Frequency Privacy of Incumbents in CBRS

Contact Info

Product

Resources

About