Core Concepts
The author presents a novel deep learning-based technique for detecting jammers in 5G networks by focusing on the Synchronization Signal Block (SSB) in the RF domain.
Abstract
The content discusses the critical role of the SSB in 5G networks and introduces a double-threshold deep learning jamming detector. The method focuses on RF domain features, improves network robustness, and achieves a high detection rate. By leveraging preprocessing blocks and Discrete Wavelet Transform, the proposed technique outperforms existing methods.
Traditional jamming detection methods are compared to the new approach, highlighting the importance of RF domain knowledge. The study showcases significant improvements in detection rates under various scenarios, emphasizing the need for advanced techniques to combat evolving threats in wireless communications.
Stats
Results show that the proposed method achieves a 96.4% detection rate in extra low jamming power.
Single threshold DNN design had an 86.0% detection rate.
Unprocessed IQ sample DNN design had an 83.2% detection rate.
Quotes
"The proposed method achieves a 96.4% detection rate in extra low jamming power."
"Our method distinguishes between normal and jammed received signals with high precision."
"The performance improvement is significant when compared to existing approaches."