Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks

Lin, Yun; Zhao, Haojun; Ma, Xuefei; Tu, Ya; Wang, Meiyu

doi:10.1109/tr.2020.3032744

Cited by 174 publications

(48 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Fig. 6, with the increase of the SNR, the accuracy of the model shows a trend of first gradually improving, and then fluctuating near a certain value, which also is also verified in [37]. The classifier on the fake signals generated by JSMA, UAP, FGSM, BIM and FDPA achieve the accuracy of 44.74%, 61.46%, 47.31%, 70.31% and 68.16%, respectively.…”

Section: F Comparison With Other Attackerssupporting

confidence: 60%

Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

Yang

He³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The recent years has witnessed a rapid development of Deep Learning (DL) based Automation Modulation Classification (AMC) methods, which has proved to outperform traditional classification approaches. In order to disturb the deep neural networks for AMC, in this paper, we propose an adversarial attack method to generate fake signals for fooling DL-based classifiers. Firstly, some constraints on visual difference and recoverability of fake signals are defined. Next, a Few Data Point Attacker (FDPA) is proposed to generate fake signals with few perturbed data points via differential evolution algorithm. Some experiments are taken on a public dataset, RML 2016.10a, and the results show that fake signals generated by the FDPA can remarkably reduce the accuracies of three types of DL-based AMC classifiers, a Convolutional Neural Network (CNN) based classifier, a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) based classifier, and a classifier combined with CNN and LSTM-RNN. The code will be available. INDEX TERMS Automatic modulation classification, fake signals, few data point attacker (FDPA), differential evolution.

show abstract

Section: F Comparison With Other Attackerssupporting

confidence: 60%

Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

Yang

He³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…With the coming of the 6G era, many advanced technologies have been extensively researched, such as artificial intelligence technology [1], image processing technology [2], intelligent integration technology [3], and wireless communication technology [4], which have also promoted the development of the IoT field. The application of IoT technology is becoming more and more important.…”

Section: Introductionmentioning

confidence: 99%

Electromagnetic Environment Portrait Based on Big Data Mining

Guo

Lin

2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

With the development of IoT in smart cities, the electromagnetic environment (EME) in cities is becoming more and more complex. A full understanding of the characteristics of past spectrum resource utilization is the key to improving the efficiency of spectrum management. In order to explore the characteristics of spectrum utilization more comprehensively, this paper designs an EME portrait model. By checking the statistical information of the spectrum data, including changes in the noise floor and channel utilization in each individual wireless service, the correlation between the spectrum and time or space of different channels and the information is merged into a high-dimensional model through consistency transformation to form the EME portrait. The portrait model is not only convenient for storage and retrieval but also beneficial for transfer and expansion, which will become an important foundation for intelligent electromagnetic spectrum management.

show abstract

“…Because the physiothermal channel of wireless communications is open, the modulation signal containing important information is fully exposed and an attacker can retrieve important signal information by utilizing a blind signal processing technology, which poses a serious threat to legal communication that makes signal data available. For this issue, Reference [13] discusses the performance of a modulation recognition attack method, measures the effectiveness of adversarial attack on signal, and empirically evaluates the reliability of CNN. In particular, privacy and safety are crucial.…”

Section: Introductionmentioning

confidence: 99%

Signal Modulation Recognition Method Based on Differential Privacy Federated Learning

Shi

et al. 2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Signal modulation recognition is widely utilized in the field of spectrum detection, channel estimation, and interference recognition. With the development of artificial intelligence, substantial advances in signal recognition utilizing deep learning approaches have been achieved. However, a huge amount of data is required for deep learning. With increasing focus on privacy and security, barriers between data sources are sometimes difficult to break. This limits the data and renders them weak, so that deep learning is not sufficient. Federated learning can be a viable way of solving this challenge. In this article, we will examine the recognition of signal modulation based on federated learning with differential privacy, and the results show that the recognition rate is acceptable while data protection and security are being met.

show abstract

Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks

Cited by 174 publications

References 30 publications

Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

Faking Signals to Fool Deep Neural Networks in AMC via Few Data Points

Electromagnetic Environment Portrait Based on Big Data Mining

Signal Modulation Recognition Method Based on Differential Privacy Federated Learning

Contact Info

Product

Resources

About