國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Deep Neural Networks for Radio Frequ...

Merchant, Kevin .

Deep Neural Networks for Radio Frequency Fingerprinting.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Deep Neural Networks for Radio Frequency Fingerprinting.
作者:	Merchant, Kevin .
出版者:	Ann Arbor : ProQuest Dissertations & Theses, 2020
面頁冊數:	148 p.
附註:	Source: Dissertations Abstracts International, Volume: 82-02, Section: B.
附註:	Advisor: Chellappa, Rama.
Contained By:	Dissertations Abstracts International82-02B.
標題:	Electrical engineering.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27667750
ISBN:	9798662446830

Deep Neural Networks for Radio Frequency Fingerprinting.
Merchant, Kevin .

Deep Neural Networks for Radio Frequency Fingerprinting. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 148 p.

Source: Dissertations Abstracts International, Volume: 82-02, Section: B.

Thesis (Ph.D.)--University of Maryland, College Park, 2020.

This item is not available from ProQuest Dissertations & Theses.

As the Internet of Things (IoT) continues to expand, there is a growing necessity for improved techniques to authenticate the identity of wireless transmitters to prevent unauthorized network access. In this dissertation, we develop a series of physical-layer authentication, or radio frequency (RF) fingerprinting, techniques which utilize methods from deep learning to train convolutional and recurrent neural network models to verify the identity of wireless transmitters which meet the IEEE 802.15.4 standard.First, we develop a technique which utilizes a convolutional neural network (CNN) to identify or verify the identity of a transmitter from which a time-domain complex baseband signal was recorded. This technique relies on an extensive pre-processing sequence to remove sources of potential bias and trivial features from the received waveforms, and derives an estimated error signal from each recording from which the CNN learns discriminatory features. We demonstrate the effectiveness of the technique on a set of seven off-the-shelf ZigBee devices recorded outside in an urban environment, as well as in a laboratory environment with artificial noise over a wide-range of signal-to-noise ratios (SNRs).Next, we train a series of models which utilize both convolutional and recurrent elements to improve the performance of the previous technique in the presence of high levels of noise and expand the evaluation to a larger set of twenty-five devices. We evaluate several realistic scenarios, including the performance in typical multipath environments and the ability to correctly reject previously unseen devices. In order to justify the proposed pre-processing sequence, we present experimental results that demonstrate weaknesses in fingerprint verification classifiers in which frequency synchronization is not performed. Finally, we present a simple technique to reduce the amount of memory required for a collection of fingerprint models by up to 95% without loss of performance.To further enhance the security of the trained fingerprint models, we propose a generative adversarial network (GAN) architecture and training procedure to provide additional training examples for the classifiers. We show that fingerprint classifiers that are trained exclusively on real devices cannot reliably reject GAN-generated signals. Furthermore, we illustrate that augmenting the training process of the fingerprint models with GAN-generated signals reduces this vulnerability, even if the GAN used for training and inference are different.Finally, we assess the practicality of transferring an RF fingerprint model from one receiver to another. Experimentally, we demonstrate significant degradation in classification performance when a fingerprint model is learned using signals recorded on one receiver and evaluated using signals recorded on another receiver. First, we show that generalization may be improved by including multiple receivers in the training process. Then, we develop a calibration procedure whereby models learned on a single receiver can be transferred without alteration to another receiver by learning a transformation function, implemented as a residual neural network, to model the variations between the two receivers. We perform several experiments with ten commercial receivers to confirm the effectiveness of the technique under realistic constraints.

ISBN: 9798662446830Subjects--Topical Terms:

454503
Electrical engineering.
Subjects--Index Terms:

Deep neural networks

Deep Neural Networks for Radio Frequency Fingerprinting.
LDR:04618nmm a2200349 4500 001 594526
005 20210521101646.5
008 210917s2020 ||||||||||||||||| ||eng d
020 $a 9798662446830
035 $a (MiAaPQ)AAI27667750
035 $a AAI27667750
040 $a MiAaPQ $c MiAaPQ
100 1 $a Merchant, Kevin . $3 886516
245 1 0 $a Deep Neural Networks for Radio Frequency Fingerprinting.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 148 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-02, Section: B.
500 $a Advisor: Chellappa, Rama.
502 $a Thesis (Ph.D.)--University of Maryland, College Park, 2020.
506 $a This item is not available from ProQuest Dissertations & Theses.
506 $a This item must not be sold to any third party vendors.
506 $a This item must not be added to any third party search indexes.
520 $a As the Internet of Things (IoT) continues to expand, there is a growing necessity for improved techniques to authenticate the identity of wireless transmitters to prevent unauthorized network access. In this dissertation, we develop a series of physical-layer authentication, or radio frequency (RF) fingerprinting, techniques which utilize methods from deep learning to train convolutional and recurrent neural network models to verify the identity of wireless transmitters which meet the IEEE 802.15.4 standard.First, we develop a technique which utilizes a convolutional neural network (CNN) to identify or verify the identity of a transmitter from which a time-domain complex baseband signal was recorded. This technique relies on an extensive pre-processing sequence to remove sources of potential bias and trivial features from the received waveforms, and derives an estimated error signal from each recording from which the CNN learns discriminatory features. We demonstrate the effectiveness of the technique on a set of seven off-the-shelf ZigBee devices recorded outside in an urban environment, as well as in a laboratory environment with artificial noise over a wide-range of signal-to-noise ratios (SNRs).Next, we train a series of models which utilize both convolutional and recurrent elements to improve the performance of the previous technique in the presence of high levels of noise and expand the evaluation to a larger set of twenty-five devices. We evaluate several realistic scenarios, including the performance in typical multipath environments and the ability to correctly reject previously unseen devices. In order to justify the proposed pre-processing sequence, we present experimental results that demonstrate weaknesses in fingerprint verification classifiers in which frequency synchronization is not performed. Finally, we present a simple technique to reduce the amount of memory required for a collection of fingerprint models by up to 95% without loss of performance.To further enhance the security of the trained fingerprint models, we propose a generative adversarial network (GAN) architecture and training procedure to provide additional training examples for the classifiers. We show that fingerprint classifiers that are trained exclusively on real devices cannot reliably reject GAN-generated signals. Furthermore, we illustrate that augmenting the training process of the fingerprint models with GAN-generated signals reduces this vulnerability, even if the GAN used for training and inference are different.Finally, we assess the practicality of transferring an RF fingerprint model from one receiver to another. Experimentally, we demonstrate significant degradation in classification performance when a fingerprint model is learned using signals recorded on one receiver and evaluated using signals recorded on another receiver. First, we show that generalization may be improved by including multiple receivers in the training process. Then, we develop a calibration procedure whereby models learned on a single receiver can be transferred without alteration to another receiver by learning a transformation function, implemented as a residual neural network, to model the variations between the two receivers. We perform several experiments with ten commercial receivers to confirm the effectiveness of the technique under realistic constraints.
590 $a School code: 0117.
650 4 $a Electrical engineering. $3 454503
650 4 $a Artificial intelligence. $3 194058
653 $a Deep neural networks
653 $a Radio frequency fingerprinting
690 $a 0544
690 $a 0800
710 2 $a University of Maryland, College Park. $b Electrical Engineering. $3 795441
773 0 $t Dissertations Abstracts International $g 82-02B.
790 $a 0117
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27667750