An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance
Abstract Increasing Internet of Things (IoT) deployments present a growing surface over which villainous actors can carry out attacks. This disturbing revelation is amplified by the fact that most IoT devices use weak or no encryption. Specific Emitter Identification (SEI) is an approach intended to...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | The Journal of Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/tje2.12327 |
| _version_ | 1797449140949483520 |
|---|---|
| author | Mohamed K. M. Fadul Donald R. Reising Lakmali P. Weerasena |
| author_facet | Mohamed K. M. Fadul Donald R. Reising Lakmali P. Weerasena |
| author_sort | Mohamed K. M. Fadul |
| collection | DOAJ |
| description | Abstract Increasing Internet of Things (IoT) deployments present a growing surface over which villainous actors can carry out attacks. This disturbing revelation is amplified by the fact that most IoT devices use weak or no encryption. Specific Emitter Identification (SEI) is an approach intended to address this IoT security weakness. This work provides the first Deep Learning (DL) driven SEI approach that upsamples the signals after collection to improve performance while reducing the hardware requirements of the IoT devices that collect them. DL‐driven upsampling results in superior SEI performance versus two traditional upsampling approaches and a convolutional neural network‐only approach. |
| first_indexed | 2024-03-09T14:21:27Z |
| format | Article |
| id | doaj.art-5599a4ba97a44bc8a443055a500e502e |
| institution | Directory Open Access Journal |
| issn | 2051-3305 |
| language | English |
| last_indexed | 2024-03-09T14:21:27Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Journal of Engineering |
| spelling | doaj.art-5599a4ba97a44bc8a443055a500e502e2023-11-28T11:02:29ZengWileyThe Journal of Engineering2051-33052023-11-01202311n/an/a10.1049/tje2.12327An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performanceMohamed K. M. Fadul0Donald R. Reising1Lakmali P. Weerasena2Electrical Engineering Department University of Tennessee at Chattanooga Chattanooga Tennessee USAElectrical Engineering Department University of Tennessee at Chattanooga Chattanooga Tennessee USADepartment of Mathematics University of Tennessee at Chattanooga Chattanooga Tennessee USAAbstract Increasing Internet of Things (IoT) deployments present a growing surface over which villainous actors can carry out attacks. This disturbing revelation is amplified by the fact that most IoT devices use weak or no encryption. Specific Emitter Identification (SEI) is an approach intended to address this IoT security weakness. This work provides the first Deep Learning (DL) driven SEI approach that upsamples the signals after collection to improve performance while reducing the hardware requirements of the IoT devices that collect them. DL‐driven upsampling results in superior SEI performance versus two traditional upsampling approaches and a convolutional neural network‐only approach.https://doi.org/10.1049/tje2.12327network securityphysical layer securitywireless communication |
| spellingShingle | Mohamed K. M. Fadul Donald R. Reising Lakmali P. Weerasena An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance The Journal of Engineering network security physical layer security wireless communication |
| title | An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance |
| title_full | An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance |
| title_fullStr | An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance |
| title_full_unstemmed | An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance |
| title_short | An investigation into the impacts of deep learning‐based re‐sampling on specific emitter identification performance |
| title_sort | investigation into the impacts of deep learning based re sampling on specific emitter identification performance |
| topic | network security physical layer security wireless communication |
| url | https://doi.org/10.1049/tje2.12327 |
| work_keys_str_mv | AT mohamedkmfadul aninvestigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance AT donaldrreising aninvestigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance AT lakmalipweerasena aninvestigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance AT mohamedkmfadul investigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance AT donaldrreising investigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance AT lakmalipweerasena investigationintotheimpactsofdeeplearningbasedresamplingonspecificemitteridentificationperformance |