Secure Deep Learning for Intelligent Terahertz Metamaterial Identification
Metamaterials, artificially engineered structures with extraordinary physical properties, offer multifaceted capabilities in interdisciplinary fields. To address the looming threat of stealthy monitoring, the detection and identification of metamaterials is the next research frontier but have not ye...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/19/5673 |
| _version_ | 1797551798554198016 |
|---|---|
| author | Feifei Liu Weihao Zhang Yu Sun Jianwei Liu Jungang Miao Feng He Xiaojun Wu |
| author_facet | Feifei Liu Weihao Zhang Yu Sun Jianwei Liu Jungang Miao Feng He Xiaojun Wu |
| author_sort | Feifei Liu |
| collection | DOAJ |
| description | Metamaterials, artificially engineered structures with extraordinary physical properties, offer multifaceted capabilities in interdisciplinary fields. To address the looming threat of stealthy monitoring, the detection and identification of metamaterials is the next research frontier but have not yet been explored. Here, we show that the crypto-oriented convolutional neural network (CNN) makes possible the secure intelligent detection of metamaterials in mixtures. Terahertz signals were encrypted by homomorphic encryption and the ciphertext was submitted to the CNN directly for results, which can only be decrypted by the data owner. The experimentally measured terahertz signals were augmented and further divided into training sets and test sets using 5-fold cross-validation. Experimental results illustrated that the model achieved an accuracy of 100% on the test sets, which highly outperformed humans and the traditional machine learning. The CNN took 9.6 s to inference on 92 encrypted test signals with homomorphic encryption backend. The proposed method with accuracy and security provides private preserving paradigm for artificial intelligence-based material identification. |
| first_indexed | 2024-03-10T15:51:10Z |
| format | Article |
| id | doaj.art-cf13b92394684f28937e91cac61b61d9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:51:10Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cf13b92394684f28937e91cac61b61d92023-11-20T16:05:22ZengMDPI AGSensors1424-82202020-10-012019567310.3390/s20195673Secure Deep Learning for Intelligent Terahertz Metamaterial IdentificationFeifei Liu0Weihao Zhang1Yu Sun2Jianwei Liu3Jungang Miao4Feng He5Xiaojun Wu6School of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaSchool of Cyber Science and Technology, Beihang University, Beijing 100191, ChinaMetamaterials, artificially engineered structures with extraordinary physical properties, offer multifaceted capabilities in interdisciplinary fields. To address the looming threat of stealthy monitoring, the detection and identification of metamaterials is the next research frontier but have not yet been explored. Here, we show that the crypto-oriented convolutional neural network (CNN) makes possible the secure intelligent detection of metamaterials in mixtures. Terahertz signals were encrypted by homomorphic encryption and the ciphertext was submitted to the CNN directly for results, which can only be decrypted by the data owner. The experimentally measured terahertz signals were augmented and further divided into training sets and test sets using 5-fold cross-validation. Experimental results illustrated that the model achieved an accuracy of 100% on the test sets, which highly outperformed humans and the traditional machine learning. The CNN took 9.6 s to inference on 92 encrypted test signals with homomorphic encryption backend. The proposed method with accuracy and security provides private preserving paradigm for artificial intelligence-based material identification.https://www.mdpi.com/1424-8220/20/19/5673metamaterial identificationdeep learninghomomorphic encryptionprivate preservingterahertz time domain spectroscopy (THz-TDS) |
| spellingShingle | Feifei Liu Weihao Zhang Yu Sun Jianwei Liu Jungang Miao Feng He Xiaojun Wu Secure Deep Learning for Intelligent Terahertz Metamaterial Identification Sensors metamaterial identification deep learning homomorphic encryption private preserving terahertz time domain spectroscopy (THz-TDS) |
| title | Secure Deep Learning for Intelligent Terahertz Metamaterial Identification |
| title_full | Secure Deep Learning for Intelligent Terahertz Metamaterial Identification |
| title_fullStr | Secure Deep Learning for Intelligent Terahertz Metamaterial Identification |
| title_full_unstemmed | Secure Deep Learning for Intelligent Terahertz Metamaterial Identification |
| title_short | Secure Deep Learning for Intelligent Terahertz Metamaterial Identification |
| title_sort | secure deep learning for intelligent terahertz metamaterial identification |
| topic | metamaterial identification deep learning homomorphic encryption private preserving terahertz time domain spectroscopy (THz-TDS) |
| url | https://www.mdpi.com/1424-8220/20/19/5673 |
| work_keys_str_mv | AT feifeiliu securedeeplearningforintelligentterahertzmetamaterialidentification AT weihaozhang securedeeplearningforintelligentterahertzmetamaterialidentification AT yusun securedeeplearningforintelligentterahertzmetamaterialidentification AT jianweiliu securedeeplearningforintelligentterahertzmetamaterialidentification AT jungangmiao securedeeplearningforintelligentterahertzmetamaterialidentification AT fenghe securedeeplearningforintelligentterahertzmetamaterialidentification AT xiaojunwu securedeeplearningforintelligentterahertzmetamaterialidentification |