This letter proposes the Dynamic Margin Meta Metric Learning (DM-MML) framework to address unknown class interference and sample scarce challenges in few-shot open set specific emitter identification. In DM-MML, the dual-loop meta-training phase adopts a hierarchical margin strategy with triple-optimization, where in the inner loop, strong margins enhance feature separability for source domain emitters and the outer loop applies weak margins to calibrate target domain distributions. This strategy simultaneously preserves open decision boundaries for potential unknown class samples. During meta testing, a collaborative decision mechanism combines distance metrics and confidence scores, enabling precise known-class identification while maintaining open-space rejection capacity for unknown classes. Experiments on the WiSig dataset demonstrate superior performance over existing benchmarks under few-shot conditions.

Specific Emitter Identification (SEI) is crucial for ensuring the security of physical layer communication. However, signal characteristics can be affected by various factors such as environmental and equipment variations. An effective SEI system must continuously learn and adapt to these changes to maintain accurate signal recognition. This study proposes an advanced domain incremental learning (DIL) framework for SEI, named Adaptive Domain-Incremental Learning with Knowledge Replay and Domain Alignment (ADIRA). ADIRA employs knowledge replay and distillation strategies, along with adaptive coefficients, to balance the model’s performance in recognizing signals across both new and old domains. To address the variations in signal data feature distributions across different domains, we introduce a domain alignment strategy based on adversarial training. This approach integrates embedding distillation loss with supervised contrastive loss, significantly enhancing the model’s adaptability to domain changes. Experimental results on two benchmark datasets demonstrate that ADIRA achieves performance only 0.42% and 1.71% lower than joint training, with replay samples constituting just 1.1% and 1.5% of the training set, effectively mitigating catastrophic forgetting.

Abstract Radio frequency fingerprint identification (RFFI) is a widely used technique for authenticating equipment. It identifies transmitters by extracting hardware defects found in the RF front end. Recent research has focused on the impact of transmitters and wireless channels on radio frequency fingerprint (RFF). Most work is based on the same receiver assumption, while the influence of the receiver on RFF remains unresolved. This paper focuses on the impact of receiver hardware characteristics on RFF and proposes a few‐shot cross‐receiver RFFI method based on feature separation. Data augmentation with noise addition and simulated channels addresses sparse sample issues and enhances the model's robustness to channel variations. Simultaneously, feature separation is realized by reducing the correlation between transmitter and receiver features through classification loss and similarity loss. We evaluate the proposed approaches using a large‐scale WiFi dataset. It is shown that when a trained transmitter classifier is deployed on new receivers with only 30 samples per trained transmitter, the average identification accuracy of the proposed method is 83.6%. This accuracy is 9.45% higher than the baseline method without considering transmitter hardware influence. After fine‐tuning, the average identification accuracy can reach 98.25%.

As a rising application paradigm, cloud computing enables the resources to be virtualized and shared among applications. In a typical cloud computing scenario, customers, Service Providers (SP), and Platform Providers (PP) are independent participants, and they have their own objectives with different revenues and costs. From PPs' viewpoints, much research work reduced the costs by optimizing VM placement and deciding when and how to perform the VM migrations. However, some work ignored the fact that the balanced use of the multi-dimensional resources can affect overall resource utilization significantly. Furthermore, some work focuses on the selection of the VMs and the target servers without considering how to perform the reconfigurations. In this paper, with a comprehensive consideration of PPs' interests, we propose a framework to improve their profits by maximizing the resource utilization and reducing the reconfiguration costs. Firstly, we use the vector arithmetic to model the objective of balancing the multi-dimensional resources use and propose a VM deployment optimization method to maximize the resource utilization. Then a two-level runtime reconfiguration strategy, including local adjustment and VM parallel migration, is presented to reduce the VM migration and shorten the total migration time. Finally, we conduct some preliminary experiments, and the results show that our framework is effective in maximizing the resource utilization and reducing the costs of the runtime reconfiguration.