This paper investigates the issue of wireless network topology inference via passive sensing of radio frequency (RF) signals without accessing their content. In non-cooperative scenarios, topology inference faces numerous challenges including the indirect, limited, and unreliable nature of available information, with no practical application instances demonstrated to date. To address these issues, we design a blind wireless network topology inference framework consisting of three key functional modules: signal detection, specific emitter identification (SEI), and topology inference. Guided by this framework, we present a systematic approach. Specifically, to confirm the identity of the detected signals, we propose a cross-domain robust SEI method based on transfer learning. These capabilities enable the mapping of raw RF signals to network interaction behaviors. Furthermore, to adapt to network dynamics and interaction behaviors across different time scales, we propose an adaptive topology inference method based on multivariate Hawkes processes (MHP) with dual timestamps. Finally, we develop an experimental validation system to evaluate the proposed framework. Experimental results demonstrate that our framework can accurately reconstruct the network topology from over-the-air RF signals, representing a significant step from theory to practice. Additional performance analysis confirms the superiority of the proposed topology inference method in both accuracy and adaptability.

Specific emitter identification (SEI) separates the radio frequency fingerprint (RFF) from signals, which is of great significance in solving Internet of Things (IoT) security problems. However, the scarcity of high-quality, diverse, and labeled data in real-world scenarios limits the application of SEI. Under such conditions, the SEI is referred to as few-shot SEI (FS-SEI). To surmount this challenge, we propose a diffusion model-based data augmentation method capable of generating a substantial volume of diverse, high-quality data. Specifically, we develop a multi-scale convolutional block attention module denoising diffusion probabilistic model (MSCBAM-DDPM), which enhances feature capture capabilities, laying the foundation for the generation of diverse data. Furthermore, we propose an adaptive two-stage multi-domain loss function that guides the model to learn the characteristics of the original data and further derive other similar features, thereby achieving the goal of generating diverse and high-quality data. Finally, we theoretically derive the feasibility of the proposed loss function and further demonstrate the excellent diversity and quality of the data generated by our method, as well as its considerable gain for FS-SEI, through extensive experiments on real-world signal datasets.

Specific emitter identification (SEI) is a physical-layer authentication technique that identifies devices by extracting radio frequency fingerprints (RFFs) from received signals. Open-set SEI (OS-SEI) refers to classifying known classes while rejecting unknown classes, which typically requires a sufficient amount of labeled training samples. However, in open-world scenarios, labeled samples are often limited, and unlabeled samples may contain unknown classes. Moreover, open-world recognition not only requires detecting unknown class samples but also identifying specific novel classes within these unknown samples and integrating them into the recognition model. Current OS-SEI methods can only categorize all unknown samples as a single class, lacking the ability to further differentiate these unknown classes. To address these challenges, we formulate a novel semi-supervised open-world SEI (SSOW-SEI) problem, which aims to overcome the shortcomings of OS-SEI in utilizing unlabeled data, distinguishing unknown classes, and addressing class distribution mismatches between labeled and unlabeled data. Furthermore, we develop an end-to-end similarity-adaptive (SAA) framework for SSOW-SEI. Specifically, after automatically extracting sample features, SAA first identifies novel classes by measuring pairwise similarities between the features, and then recognizes known classes using adaptive cross-entropy, which balances the learning rate between known and novel classes to prevent model bias toward known classes. Additionally, entropy regularization is applied to mitigate model overfitting. Extensive experimental results demonstrate that the proposed SAA framework effectively leverages limited labeled data, handles large volumes of unlabeled data, and accurately identifies both known and novel classes. The results also highlight its strong generalization, stability, and enhanced adaptability to novel classes.

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.