Specific emitter identification (SEI) is a device identification technology that extracts radio frequency (RF) fingerprint from received signals. However, channel effects on RF fingerprint can vary between the training and testing stage, and SEI based on deep learning (DL) will be unable to withstand channel changes. To address this problem, we propose a channel-robust SEI scheme driven by causal learning. We analyze received signals from the causal perspective and construct a structural causal model (SCM) of SEI. In the SCM, received signals are considered as mixtures of the causal element and interference element, and only the former affects identification. Additionally, we design a new RF fingerprint feature representation called the centralized logarithmic power spectrum (CLPS) to reduce the impact of channel effects. Furthermore, we propose a causal purification network (CPNet) driven by causality to further alleviate channel effects. CPNet weakens the spurious associations between the channel and emitter labels through feature decorrelation and feature purification, strengthens the correlation between RF fingerprint and labels, and improves the generalization of SEI. Finally, our approach is evaluated extensively using 20 ZigBee devices under different channel environments. Experimental results demonstrate that our scheme can effectively alleviate channel effects, improve SEI performance under various channel environments, and exhibit good generalization and stability.

With the extensive research of multiantenna technology, beamforming (BF) will play an important role in the future communication systems due to its high transmission gain and satisfying directivity. If we can detect the non-cooperative beams, it is of great significance in counter reconnaissance, beam tracking, and spectrum sensing of multiantenna transmitters. This paper investigates the wireless sensor networks (WSNs), which is used to detect the unknown non-cooperative beam signal. In order to perceive the presence of beam signals without the prior information, we first derive the detection probability based on the sensors’ received signal strength (RSS). Then, based on the strong directivity of the beam signal, we propose an improved “k rank” fusion algorithm by jointly exploiting the energy detection (ED) information and location information of the sensors. Finally, the beam detection performance of different fusion algorithms is compared in simulation, and we find that our proposed algorithm showed better detection probability and lower error probability. The simulation results verify the correctness and effectiveness of the proposed algorithm.