Open Set Recognition of Communication Signal Modulation Based on Deep Learning

Zhang, Xinliang; Li, Tianyun; Gong, Pei; Liu, Renwei; Zha, Xiong; Tang, Wenqi

doi:10.1109/lcomm.2022.3174035

Cited by 25 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ref. [27], the author proposes a DL-based OSR method for wireless communication signal modulation, which improves the generalized end-to-end loss for training neural networks, increases the similarity of feature vectors of the same modulation type, and reduces the similarity of feature vector quantities of different types. Bassey et al [28] proposed a new intrusion detection method to detect unauthorized IoT devices.…”

Section: Related Workmentioning

confidence: 99%

Research on the Enhancement Method of Specific Emitter Open Set Recognition

Sun,

Du,

Qiao

et al. 2023

Electronics

View full text Add to dashboard Cite

Open set recognition (OSR) aims at dealing with unknown classes that are not included in the train set. However, existing OSR methods rely on deep learning networks that perform supervised learning on known classes in the train set, resulting in poor performance when the unknown class is very similar to the known class. Considering the subtle individual differences under the same type in specific emitter identification (SEI) applications, it is difficult to distinguish between known classes and unknown classes in open set scenarios. This paper proposes a pseudo signal generation and recognition neural network (PSGRNN) to address relevant problems in this situation. PSGRNN applies complex-value convolution operations to accommodate IQ signal inputs. Its key idea is to utilize samples of known classes to generate pseudo samples of unknown classes. Then, the samples of known classes and the generated pseudo samples of unknown classes are jointly input into the neural network to construct a new classification task for training. Moreover, the center loss is improved by adding inter-class penalties to maximize the inter-class difference. This helps to learn useful information for separating known and unknown classes, resulting in clearer decision boundaries between the known and the unknown. Extensive experiments on various benchmark signal datasets indicate that the proposed method achieves more accurate and robust open set classification results, with an average accuracy improvement of 4.62%.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on the Enhancement Method of Specific Emitter Open Set Recognition

Sun,

Du,

Qiao

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Additionally, DL-based MR plays a crucial role in signal detection, spectrum management, and signal control. For example, Zhang et al [5] proposed a DL-based method for MR, using a neural network with an improved generalized endto-end loss to enhance similarity among feature vectors with the same modulation type and reduce similarity among those with different types. Wang et al [6] developed a Multi-Cue Fusion network for automatic modulation recognition, while Njoku et al [7] introduced an economically efficient hybrid neural network consisting of a shallow convolutional network, gated recurrent units, and deep neural network (DNN), for automatic modulation recognition in cognitive radios.…”

Section: Introductionmentioning

confidence: 99%

Attacking Modulation Recognition With Adversarial Federated Learning in Cognitive-Radio-Enabled IoT

Zhang,

Liu,

Chen

et al. 2024

IEEE Internet Things J.

View full text Add to dashboard Cite

Internet of Things (IoT) based on cognitive radio (CR) exhibits strong dynamic sensing and intelligent decisionmaking capabilities by effectively utilizing spectrum resources. The federal learning (FL) framework based modulation recognition (MR) is an essential component, but its use of uninterpretable deep learning (DL) introduces security risks. This paper combines traditional signal interference methods and data poisoning in FL to propose a new adversarial attack approach. The poisoning attack in distributed frameworks manipulates the global model by controlling malicious users, which is not only covert but also highly impactful. The carefully designed pseudo-noise in MR is also extremely difficult to detect. The combination of these two techniques can generate a greater security threat. We have further advanced our proposal with the introduction of the new adversarial attack method called "Chaotic Poisoning Attack" to reduce the recognition accuracy of the FL-based MR system. We establish effective attack conditions, and simulation results demonstrate that our method can cause a decrease of approximately 80% in the accuracy of the local model under weak perturbations and a decrease of around 20% in the accuracy of the global model. Compared to white-box attack methods, our method exhibits superior performance and transferability.

show abstract

“…To train the model, SDFEN introduces a hybrid loss function that improves the form of the loss function. Almost all existing OSR methods adopt threshold-based classification schemes from the perspective of discriminative models [24,38,39]. A feature comparator compares depth features and thresholds to recognize unknowns.…”

Section: Introductionmentioning

confidence: 99%

Spatial Distribution Feature Extraction Network for Open Set Recognition of Electromagnetic Signal

Zhang,

Zhou,

Wang

et al. 2024

CMES

View full text Add to dashboard Cite

This paper proposes a novel open set recognition method, the Spatial Distribution Feature Extraction Network (SDFEN), to address the problem of electromagnetic signal recognition in an open environment. The spatial distribution feature extraction layer in SDFEN replaces convolutional output neural networks with the spatial distribution features that focus more on inter-sample information by incorporating class center vectors. The designed hybrid loss function considers both intra-class distance and inter-class distance, thereby enhancing the similarity among samples of the same class and increasing the dissimilarity between samples of different classes during training. Consequently, this method allows unknown classes to occupy a larger space in the feature space. This reduces the possibility of overlap with known class samples and makes the boundaries between known and unknown samples more distinct. Additionally, the feature comparator threshold can be used to reject unknown samples. For signal open set recognition, seven methods, including the proposed method, are applied to two kinds of electromagnetic signal data: modulation signal and real-world emitter. The experimental results demonstrate that the proposed method outperforms the other six methods overall in a simulated open environment. Specifically, compared to the state-of-the-art Openmax method, the novel method achieves up to 8.87% and 5.25% higher micro-F-measures, respectively.

show abstract

Open Set Recognition of Communication Signal Modulation Based on Deep Learning

Cited by 25 publications

References 11 publications

Research on the Enhancement Method of Specific Emitter Open Set Recognition

Research on the Enhancement Method of Specific Emitter Open Set Recognition

Attacking Modulation Recognition With Adversarial Federated Learning in Cognitive-Radio-Enabled IoT

Spatial Distribution Feature Extraction Network for Open Set Recognition of Electromagnetic Signal

Contact Info

Product

Resources

About