Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging
Optical encryption based on single-pixel imaging (SPI) has made great advances with the introduction of deep learning. However, the use of deep neural networks usually requires a long training time, and the networks need to be retrained once the target scene changes. With this in mind, we propose an...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/3/1012 |
| _version_ | 1797318175930449920 |
|---|---|
| author | Wen-Kai Yu Shuo-Fei Wang Ke-Qian Shang |
| author_facet | Wen-Kai Yu Shuo-Fei Wang Ke-Qian Shang |
| author_sort | Wen-Kai Yu |
| collection | DOAJ |
| description | Optical encryption based on single-pixel imaging (SPI) has made great advances with the introduction of deep learning. However, the use of deep neural networks usually requires a long training time, and the networks need to be retrained once the target scene changes. With this in mind, we propose an SPI encryption scheme based on an attention-inserted physics-driven neural network. Here, an attention module is used to encrypt the single-pixel measurement value sequences of two images, together with a sequence of cryptographic keys, into a one-dimensional ciphertext signal to complete image encryption. Then, the encrypted signal is fed into a physics-driven neural network for high-fidelity decoding (i.e., decryption). This scheme eliminates the need for pre-training the network and gives more freedom to spatial modulation. Both simulation and experimental results have demonstrated the feasibility and eavesdropping resistance of this scheme. Thus, it will lead SPI-based optical encryption closer to intelligent deep encryption. |
| first_indexed | 2024-03-08T03:48:40Z |
| format | Article |
| id | doaj.art-43b5dbe7dd4b4c6e80fe2237a436c40d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T03:48:40Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-43b5dbe7dd4b4c6e80fe2237a436c40d2024-02-09T15:22:34ZengMDPI AGSensors1424-82202024-02-01243101210.3390/s24031012Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel ImagingWen-Kai Yu0Shuo-Fei Wang1Ke-Qian Shang2Center for Quantum Technology Research, Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement of Ministry of Education, School of Physics, Beijing Institute of Technology, Beijing 100081, ChinaCenter for Quantum Technology Research, Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement of Ministry of Education, School of Physics, Beijing Institute of Technology, Beijing 100081, ChinaCenter for Quantum Technology Research, Key Laboratory of Advanced Optoelectronic Quantum Architecture and Measurement of Ministry of Education, School of Physics, Beijing Institute of Technology, Beijing 100081, ChinaOptical encryption based on single-pixel imaging (SPI) has made great advances with the introduction of deep learning. However, the use of deep neural networks usually requires a long training time, and the networks need to be retrained once the target scene changes. With this in mind, we propose an SPI encryption scheme based on an attention-inserted physics-driven neural network. Here, an attention module is used to encrypt the single-pixel measurement value sequences of two images, together with a sequence of cryptographic keys, into a one-dimensional ciphertext signal to complete image encryption. Then, the encrypted signal is fed into a physics-driven neural network for high-fidelity decoding (i.e., decryption). This scheme eliminates the need for pre-training the network and gives more freedom to spatial modulation. Both simulation and experimental results have demonstrated the feasibility and eavesdropping resistance of this scheme. Thus, it will lead SPI-based optical encryption closer to intelligent deep encryption.https://www.mdpi.com/1424-8220/24/3/1012optical encryptionsingle-pixel imagingimage reconstructionattention modulephysics-driven neural network |
| spellingShingle | Wen-Kai Yu Shuo-Fei Wang Ke-Qian Shang Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging Sensors optical encryption single-pixel imaging image reconstruction attention module physics-driven neural network |
| title | Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging |
| title_full | Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging |
| title_fullStr | Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging |
| title_full_unstemmed | Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging |
| title_short | Optical Encryption Using Attention-Inserted Physics-Driven Single-Pixel Imaging |
| title_sort | optical encryption using attention inserted physics driven single pixel imaging |
| topic | optical encryption single-pixel imaging image reconstruction attention module physics-driven neural network |
| url | https://www.mdpi.com/1424-8220/24/3/1012 |
| work_keys_str_mv | AT wenkaiyu opticalencryptionusingattentioninsertedphysicsdrivensinglepixelimaging AT shuofeiwang opticalencryptionusingattentioninsertedphysicsdrivensinglepixelimaging AT keqianshang opticalencryptionusingattentioninsertedphysicsdrivensinglepixelimaging |