Satellite-terrestrial-integrated internet of things (IoT) is an inevitable trend in future development, but open satellite link and massive IoT device access will bring serious security risks. However, most existing recognition models are unable to discover and reject malicious IoT devices since they lack the decision information of these unauthorized devices during training. To address this dilemma, this paper proposes a knowledge inference and sharing-based open-set recognition approach to protect satellite-terrestrial-integrated IoT. It proceeds in two steps. First, knowledge inference, where we construct ideal substitutes for unauthorized devices after reasonable inference on the training set, aims to compensate the model’s missing decision information. Second, knowledge sharing, where we inherit the existing knowledge and modify the model’s decision boundaries through model expansion and knowledge distillation, achieves accurate open-set recognition. Experiments on the ORACLE dataset demonstrated that our approach outperforms other state-of-the-art OSR methods in terms of accuracy and running time. In short, our approach has excellent performance while only slightly increasing computational complexity.

In the integration of terrestrial and non‐terrestrial networks, massive access to wireless signals poses a significant threat to communication systems. However, existing signal recognition models cannot accurately identify signals with low signal‐to‐noise ratios (SNRs). To alleviate this issue, this paper proposes a high‐efficient information extraction mechanism based on complex convolution. Specifically, complex convolution and complex max‐pooling operations have been integrated into a real‐value network to efficiently acquire anti‐noise information. The extracted features contain both in‐phase and quadrature (IQ) structure information and complex relationship information. Experiments on the public RML2016.04C dataset indicated that the model exhibits rapid convergence and superior noise‐robustness under low SNRs. When SNR =0 dB, the model outperforms the suboptimal model by 4.05%. Furthermore, our model demonstrates excellent generalization performance at high SNRs.

The efficacy of data-driven automatic target recognition (ATR) algorithms relies on the prior knowledge acquired from the target sample set. However, the lack of knowledge of high-value unknown target samples hinders the practical application of existing ATR models, as the acquisition of this SAR imagery is often challenging. In this paper, we propose an out-of-distribution knowledge inference-based approach for the implementation of open-set-recognition tasks in SAR imagery. The proposed method integrates two modules: out-of-distribution feature inference and a knowledge-sharing retrain mechanism. First, the proposed out-of-distribution feature inference module aims to provide the requisite prior knowledge for the ATR model to effectively recognize unknown target samples. Furthermore, the aforementioned module also employs a compact feature extraction scheme to mitigate the potential overlap between the constructed out-of-distribution feature distribution and the known sample feature distribution. Finally, the proposed method employs the novel knowledge-sharing retraining mechanism to learn prior knowledge of unknown SAR target samples. Several experimental results show the superiority of the proposed approach based on the Moving and Stationary Target Acquisition and Recognition (MSTAR) data set. Some ablation experiments also demonstrate the role of each module of the proposed approach. Even when one category of target sample information is completely absent from the training set, the recognition accuracy of the proposed approach still achieves $90.31\%$.