Signal detection effects on deep neural networks utilizing raw IQ for modulation classification

Hauser, Steven C.; Headley, William C.; Michaels, Alan J.

doi:10.1109/milcom.2017.8170853

Cited by 46 publications

(33 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The roll-off factor of the root raised cosine was varied uniformly from 0.34 to 0.36 with a step size of 0.01. For the channel model, the modulated signal was subjected to AWGN and given a center frequency offset as described by (10) to simulate errors in the receiver's signal detection stage [33] . The power of the AWGN is calculated using E s /N o and varied uniformly from 0 dB to 20 dB with a step size of 2.…”

Section: Automatic Modulation Classification Target Networkmentioning

confidence: 99%

“…One effect shown in [33] was the consequences of errors in center frequency estimation, resulting in frequency offset signals. The authors of [33] found that raw-IQ based AMC only generalized over the training distribution it was provided and therefore if additional frequency offsets outside of the training distribution were encountered, the classification accuracy would suffer. Because these estimations are never exact, adversarial examples transmitted over the air must also generalize over these effects.…”

Section: B Frequency Offsetmentioning

confidence: 99%

See 1 more Smart Citation

Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications

Flowers

Buehrer

Headley

2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

107

View full text Add to dashboard Cite

Recent advancements in radio frequency machine learning (RFML) have demonstrated the use of raw in-phase and quadrature (IQ) samples for multiple spectrum sensing tasks. Yet, deep learning techniques have been shown, in other applications, to be vulnerable to adversarial machine learning (ML) techniques, which seek to craft small perturbations that are added to the input to cause a misclassification. The current work differentiates the threats that adversarial ML poses to RFML systems based on where the attack is executed from: direct access to classifier input, synchronously transmitted over the air (OTA), or asynchronously transmitted from a separate device. Additionally, the current work develops a methodology for evaluating adversarial success in the context of wireless communications, where the primary metric of interest is bit error rate and not human perception, as is the case in image recognition. The methodology is demonstrated using the well known Fast Gradient Sign Method to evaluate the vulnerabilities of raw IQ based Automatic Modulation Classification and concludes RFML is vulnerable to adversarial examples, even in OTA attacks. However, RFML domain specific receiver effects, which would be encountered in an OTA attack, can present significant impairments to adversarial evasion.

show abstract

Section: Automatic Modulation Classification Target Networkmentioning

confidence: 99%

Section: B Frequency Offsetmentioning

confidence: 99%

Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications

Flowers

Buehrer

Headley

2020

IEEE Trans.Inform.Forensic Secur.

Self Cite

107

View full text Add to dashboard Cite

show abstract

“…This method is an integrated learning approach. Hauser et al [ 20 ] discussed how the classification performance of modulation signals is affected by sampling rate offsets and frequency offsets. This research demonstrates that training CNN over frequency and sample rate offsets does not have significant impact on performance.…”

Section: Related Workmentioning

confidence: 99%

Generative Adversarial Networks-Based Semi-Supervised Automatic Modulation Recognition for Cognitive Radio Networks

Zhang

2018

Sensors

View full text Add to dashboard Cite

With the recently explosive growth of deep learning, automatic modulation recognition has undergone rapid development. Most of the newly proposed methods are dependent on large numbers of labeled samples. We are committed to using fewer labeled samples to perform automatic modulation recognition in the cognitive radio domain. Here, a semi-supervised learning method based on adversarial training is proposed which is called signal classifier generative adversarial network. Most of the prior methods based on this technology involve computer vision applications. However, we improve the existing network structure of a generative adversarial network by adding the encoder network and a signal spatial transform module, allowing our framework to address radio signal processing tasks more efficiently. These two technical improvements effectively avoid nonconvergence and mode collapse problems caused by the complexity of the radio signals. The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%. In addition, we verify the advantages of our method in a semi-supervised scenario and obtain a significant increase in accuracy compared with traditional semi-supervised learning methods.

show abstract

“…To our best of knowledge, CLDNN is widely used in voice processing involving raw time-domain signals, but its application in wireless signals is still rare. In [28], convolutional neural network was used for AMC to extract features from baseband signal samples. However, the absence of simulations of model mismatches makes this method less convincing.…”

Section: Introductionmentioning

confidence: 99%

Automatic Modulation Classification Using Compressive Convolutional Neural Network

Huang

Chai

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.INDEX TERMS Automatic modulation classification, compressive loss constraint, deep convolutional neural network, multiple constellation images.

show abstract

Signal detection effects on deep neural networks utilizing raw IQ for modulation classification

Cited by 46 publications

References 12 publications

Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications

Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications

Generative Adversarial Networks-Based Semi-Supervised Automatic Modulation Recognition for Cognitive Radio Networks

Automatic Modulation Classification Using Compressive Convolutional Neural Network

Contact Info

Product

Resources

About