With the evolution of 5G wireless communications, the Synchronization Signal Block (SSB) plays a critical role in the synchronization of devices and accessibility of services. However, due to the predictable nature of SSB transmission, including the Primary and Secondary Synchronization Signals (PSS and SSS), jamming attacks are critical threats. By leveraging RF domain knowledge, this work presents a novel deep learning-based technique for detecting jammers in 5G networks. Unlike the existing jamming detection algorithms that mostly rely on network parameters, we introduce a double threshold deep learning jamming detector by focusing on the SSB. The detection method is focused on RF domain features and improves the robustness of the network without requiring integration with the pre-existing network infrastructure. By integrating a preprocessing block that extracts PSS correlation and energy per null resource elements (EPNRE) characteristics, our method distinguishes between normal and jammed received signals with high precision. Additionally, by incorporation of Discrete Wavelet Transform (DWT), the efficacy of training and detection are optimized. A double threshold double Deep Neural Network (DT-DDNN) is also introduced to the architecture complemented by a deep cascade learning model to increase the sensitivity of the model to variations of signal to jamming noise ratio (SJNR). Results show that the proposed method achieves 96.4% detection rate in extra low jamming power, i.e., SJNR between 15 to 30 dB which outperforms the single threshold DNN design with 86.0% detection rate and unprocessed IQ sample DNN design with 83.2% detection rate. Ultimately, performance of DT-DDNN is validated through the analysis of real 5G signals obtained from a practical testbed, demonstrating a strong alignment with the simulation results.

翻译：随着5G无线通信技术的发展，同步信号块（SSB）在设备同步及服务接入中发挥着关键作用。然而，由于SSB传输具有可预测性（包括主同步信号PSS和辅同步信号SSS），干扰攻击已成为重大威胁。本文利用射频域知识，提出一种基于深度学习的新型5G网络干扰检测技术。与现有大多依赖网络参数的干扰检测算法不同，我们通过聚焦SSB信号，引入了双阈值深度学习干扰检测器。该检测方法基于射频域特征，无需整合现有网络基础设施即可增强网络鲁棒性。通过集成预处理模块提取PSS相关性和空资源单元能量（EPNRE）特征，我们的方法能够以高精度区分正常接收信号与受干扰信号。此外，通过引入离散小波变换（DWT），训练与检测效率均得到优化。架构中进一步引入双阈值双深度神经网络（DT-DDNN），并辅以深度级联学习模型，以提升模型对信号与干扰噪声比（SJNR）变化的敏感度。实验结果表明，该方法在极低干扰功率条件下（即SJNR为15至30 dB）可实现96.4%的检测率，显著优于单阈值DNN设计的86.0%检测率和未处理IQ样本DNN设计的83.2%检测率。最后，通过实际测试平台获取的真实5G信号验证了DT-DDNN的性能，其结果与仿真结果高度吻合。