CN114915398A - Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium - Google Patents
Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114915398A CN114915398A CN202210466207.2A CN202210466207A CN114915398A CN 114915398 A CN114915398 A CN 114915398A CN 202210466207 A CN202210466207 A CN 202210466207A CN 114915398 A CN114915398 A CN 114915398A
- Authority
- CN
- China
- Prior art keywords
- sequence
- encoder
- chaotic
- variational self
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/001—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using chaotic signals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04Q—SELECTING
- H04Q11/00—Selecting arrangements for multiplex systems
- H04Q11/0001—Selecting arrangements for multiplex systems using optical switching
- H04Q11/0062—Network aspects
- H04Q11/0067—Provisions for optical access or distribution networks, e.g. Gigabit Ethernet Passive Optical Network (GE-PON), ATM-based Passive Optical Network (A-PON), PON-Ring
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Error Detection And Correction (AREA)
Abstract
The invention discloses a chaos encryption method based on a variational self-encoder, an application, computer equipment and a storage medium, wherein the chaos encryption method comprises the steps of obtaining an original chaos sequence; inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence; and carrying out phase covering encryption and frequency covering encryption on the communication data according to the obtained reconstructed chaotic sequence. The variational self-encoder model comprises an encoder network and a decoder network, wherein the encoder network comprises residual connecting blocks and self-attention layers which are alternately arranged, and the decoder network comprises convolutional layers and a loss layer arranged behind each convolutional layer. By introducing the variational self-encoder model, the generation rule of the chaotic sequence is learned, the low-efficiency chaotic sequence generation of a linear differential equation is replaced, the model expression capacity and generalization capacity are trained through a large amount of chaotic sequence training data, the generation efficiency of the chaotic sequence can be effectively improved, and the transmission performance is ensured.
Description
Technical Field
The invention relates to a variational self-encoder-based chaotic encryption method, application, computer equipment and a storage medium, and belongs to the technical field of communication transmission.
Background
With the development of 5G networks, big data, internet of things and other technologies, the requirements of transmission networks on capacity and efficiency are continuously improved. A passive optical access network (PON) is an important component of data transmission of a communication physical layer, downlink signal transmission is in a broadcast mode, and data transmitted by the PON is easily intercepted and attacked by an illegal user.
The chaotic secure communication is to generate a chaotic sequence by adopting a chaotic model and to carry out covering encryption on signals in a communication system according to the chaotic sequence. In an optical communication system, chaos pseudo-randomness and initial value sensitivity are main guarantees of the safety of a chaos model. However, the model of the chaotic sequence is obtained by linear iterative differential equation calculation, and the serial calculation usually requires more operation resources, and as the demand of the number of the chaotic sequences increases, the efficiency of the chaotic communication encryption scheme is affected to a certain extent.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a chaos encryption method based on a variational self-encoder, an application, a computer device and a storage medium.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
in a first aspect, the present invention provides a chaos encryption method based on a variational self-encoder, including:
the variational self-encoder model comprises an encoder network and a decoder network, wherein the encoder network comprises residual connecting blocks and self-attention layers which are alternately arranged, and the decoder network comprises convolutional layers and a loss layer arranged behind each convolutional layer;
the chaotic encryption method comprises the following steps:
obtaining an original chaotic sequence;
inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence;
carrying out phase covering encryption and frequency covering encryption on communication data according to the obtained reconstructed chaotic sequence;
the reconstruction chaotic sequence comprises a first chaotic sequence capable of carrying out phase covering on communication data and a second chaotic sequence for carrying out frequency covering on the communication data.
Further, the training method of the variational self-coder model comprises the following steps:
acquiring an original sequence for training;
inputting the obtained original sequence into an encoder network for data encoding processing, and outputting a middle sequence with deviation from the original sequence, wherein the deviation of the middle sequence comprises a standard deviation and a mean vector;
and inputting the intermediate sequence into a decoder network for data decoding processing, performing iterative training by setting an adjustable training period to make a model loss function converge, and outputting a reconstruction sequence to finish the training of the variational self-encoder model.
Further, the encoder network comprises 1 convolutional layer, 3 residual connection blocks and 2 self-attention layers;
the input original sequence is subjected to data compression processing through a convolutional layer, a ReLu function is adopted as an activation function, then dimension reduction processing is performed through 3 alternately arranged residual error connecting blocks and 2 self-attention layers, and finally a low-dimensional intermediate sequence is output.
Further, the convolution kernel size is 5, and the step size is 2.
Further, the decoder network includes 2 3 × 3 convolutional layers, 2 batch normalization layers, and 1 fully-connected layer, and a lost layer is connected after each 3 × 3 convolutional layer;
the intermediate sequence output by the encoder network firstly passes through a 3 x 3 convolutional layer, a loss layer and a normalization layer, is processed by a ReLu activation function, then passes through the 3 x 3 convolutional layer, the loss layer and the normalization layer, is processed by a full connection layer, and outputs reconstruction training, and if the loss function of the model reaches a preset condition, the intermediate sequence data is directly used as the output of the decoder network.
Further, the convolution kernel size of the 3 × 3 convolutional layer is 1, and the loss rate of the missing layer is 0.2.
Further, the loss function is a minimum loss function, and the calculation formula includes:
where σ is the standard deviation of the encoder network output; m is an average vector output by the encoder network; n is the data dimension of the original sequence input by the encoder network; i represents the ith value in the standard deviation vector; p is a radical of E (x | y) is the probability of outputting y when the encoder network input is x; p is a radical of D (y | x) is the probability of outputting x when the decoder network input is y;
the second objective of the present invention is to provide an application of a variational self-encoder based chaotic encryption method, which is applied to an orthogonal frequency division multiplexing passive optical access communication system for data encryption transmission, and the communication system includes:
the transmitting end is used for inputting an original data sequence, performing serial-parallel exchange, and mapping the original data sequence after serial-parallel exchange to a first chaotic sequence through quadrature amplitude modulation for phase covering; mapping the original data sequence after quadrature amplitude modulation to a second chaotic sequence through subcarrier modulation for frequency covering; converting the original data sequence modulated by the subcarrier from a frequency domain to a time domain through fast Fourier transform, and inputting the signals into an optical fiber after parallel-serial conversion;
and the receiving end is used for receiving the signal output to the optical fiber by the transmitting end and decrypting the signal, wherein the decryption process is the inverse transformation of the transmitting end.
It is a third object of the present invention to provide a computer apparatus comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any of the above.
A fourth object of the invention is to provide a computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, carries out the steps of any of the methods described above.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the invention, by introducing a variational self-encoder model, learning the generation rule of the chaotic sequence and utilizing the advantage of deep network parallel computation to replace the low-efficiency chaotic sequence generation of a linear solution differential equation, through a large amount of chaotic sequence training data, a network model with strong model expression capability and generalization capability is trained, the generation efficiency of the chaotic sequence can be effectively improved, and the transmission performance is ensured;
(2) by applying the chaos encryption method based on the variational self-encoder model to an orthogonal frequency division multiplexing passive optical access network (OFDM-PON) and adopting training materials of different chaos safety schemes, the encoder can learn complex structures of data distribution in various chaos models, and finally has the capacity of generating a large-space key group, thereby effectively improving the safety of the OFDM-PON system.
Drawings
FIG. 1 is a flow chart of a chaotic encryption method in one embodiment;
FIG. 2 is a diagram of a network structure of a diversity auto-encoder according to one embodiment;
FIG. 3 is a block diagram of an encoder network according to an embodiment;
FIG. 4 is a block diagram of a decoder network according to one embodiment;
FIG. 5 is a block diagram of a chaotic encryption experimental model in the first embodiment;
FIG. 6 is a diagram of the signal error rate V.S. received optical power of Probability Shaping (PS) -16 Quadrature Amplitude Modulation (QAM) in the chaos encryption experiment in the first embodiment;
fig. 7 is a calculation time v.s. chaotic sequence iteration number of the chaotic encryption experiment in the first embodiment;
fig. 8 is a flowchart of an application method of the chaotic encryption method in the OFDM-PON system in the second embodiment.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention aims to disclose a chaos encryption method based on a variational self-encoder, which is applied to the field of chaos secret communication. Aiming at an elastic optical network chaotic sequence encryption scheme based on secret communication, a depth generation model, namely a variational self-encoder model, is introduced, an original chaotic sequence is used for training a variational self-encoder, and a sequence generated by the variational self-encoder model is used for encryption. The chaos encryption method is applied to encryption transmission of quadrature amplitude modulation (16QAM) signals, and sequences generated by a variational self-encoder model are utilized to encrypt and cover the phase distribution of constellation points of uniform signal points and the positions of subcarriers corresponding to each signal at a transmitting end. The same initial key is used for generating a decryption sequence at a receiving end, the decryption sequence which is the same as that of the transmitting end can be obtained due to the robustness of the variational self-encoder, and the original data can be obtained by respectively carrying out inverse operation on the positions of the subcarriers and the phase distribution of the constellation points. The encryption method generates huge key space through deep learning and carries out encryption processing on the sending signal twice, a one-time-pad encryption mode with equal key quantity and sending data can be achieved, leakage of important files can be avoided when the important files are transmitted, and complexity and safety of the system are greatly enhanced. Meanwhile, the scheme can learn the characteristics of different chaotic models to obtain chaotic sequences with good confidentiality; the advantages of parallel computation of the graphics processor in deep learning are fully utilized, the efficiency of the chaotic encryption system is effectively improved, and good transmission performance is guaranteed.
The first embodiment is as follows:
as shown in fig. 1, the present embodiment provides a chaotic encryption method based on a variational self-encoder, including:
s01: obtaining an original chaotic sequence;
s02: inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence;
s03: and carrying out phase covering encryption and frequency covering encryption on the communication data according to the obtained reconstructed chaotic sequence.
The reconstructed chaotic sequence comprises a first chaotic sequence capable of carrying out phase covering on communication data and a second chaotic sequence for carrying out frequency covering on the communication data.
The chaos encryption method based on the variational self-encoder is realized through the following stages.
Firstly, constructing a variational auto-encoder model
As shown in fig. 3 and 4, the variational self-coder model according to the present embodiment includes a coder network and a decoder network. The encoder network includes 1 convolutional layer, 3 residual connection blocks, and 2 self-attention layers. The input original sequence is subjected to data compression processing through a convolutional layer, a ReLu function is adopted as an activation function, a pooling layer is cancelled, and dimension reduction of data is realized through Stride; then, dimension reduction processing is carried out through 3 residual error connecting blocks and 2 self-attention layers which are alternately arranged, and finally a low-dimensional intermediate sequence is output. The convolution kernel size of the convolution layer in the encoder network is 5, with a step size of 2. The decoder network comprises 2 3 × 3 convolutional layers, 2 batch normalization layers and 1 fully-connected layer, wherein a lost layer is connected after each 3 × 3 convolutional layer. The intermediate sequence output by the encoder network firstly passes through a 3 x 3 convolutional layer, a loss layer and a normalization layer, is processed by a ReLu activation function, then passes through the 3 x 3 convolutional layer, the loss layer and the normalization layer, is processed by a full connection layer, and outputs reconstruction training, and if the loss function of the model reaches a preset condition, the intermediate sequence data is directly used as the output of the decoder network. The convolutional kernel size of the 3 × 3 convolutional layers in the decoder network is 1, and the loss rate of the lost layer is 0.2.
Two, training variational self-coder model
As shown in fig. 2, the training method of the variational auto-encoder model includes:
s11: obtaining an original sequence for training, and adopting various chaotic sequences output by a chaotic model in the prior art as training sequences;
s12: inputting the obtained original sequence into an encoder network for data encoding processing, and outputting a middle sequence with deviation from the original sequence, wherein the deviation of the middle sequence comprises a standard deviation and a mean vector;
s13: and inputting the intermediate sequence into a decoder network for data decoding processing, performing iterative training by setting an adjustable training period to make a model loss function converge, and outputting a reconstruction sequence to finish the training of the variational self-encoder model.
To minimize reconstruction errors, the present embodiment employs a minimization loss function by which the variational self-coder model can learn the data distributions of various original sequences and reconstruct new data samples. The expression is as follows:
where σ is the standard deviation of the encoder network output; m is an average vector output by the encoder network; n is the data dimension of the original sequence input by the encoder network; i represents the ith value in the standard deviation vector; p is a radical of E (x | y) is the probability of outputting y when the encoder network input is x; p is a radical of D (y | x) is the probability of outputting x when the decoder network input is y;
thirdly, reconstructing the original chaos sequence
And inputting the original chaotic sequence into a trained variational self-encoder model, and outputting to obtain a reconstructed chaotic sequence, wherein the reconstructed chaotic sequence comprises a first chaotic sequence capable of masking the phase of communication data and a second chaotic sequence capable of masking the frequency of the communication data.
The first test example:
in order to test the effect of the chaos encryption method based on the variational self-encoder model in the first embodiment, as shown in fig. 5, an experimental system of the chaos encryption method based on the variational self-encoder in the first embodiment is a dual-polarization coherent optical system. At the transmitting end, the encrypted information is first generated by an arbitrary waveform generator and sent to an in-phase/quadrature modulator. The light source is a continuous wave laser working at 1550nm and with optical power of 14.5dBm, and an optical signal output by the light source is injected into the in-phase/quadrature modulator and amplified by the erbium-doped fiber amplifier to obtain a modulation signal. After that, the modulated signal is transmitted through a standard single mode fiber of 25km and inputted to the receiving end. At the receiving end, an optically tunable filter is used to suppress the spontaneous emission noise of the amplifier, and a coherent receiver is used to receive and initially demodulate the received signal. The local oscillator and the mixed signal oscilloscope are used for displaying and outputting the received signals in the form of digital files.
As shown in fig. 6, based on the PS-16QAM error rate versus received optical power, the error rate of illegal reception is maintained around 0.5, which means that all signals are misidentified. When the error rate is 1 x 10 -3 And the receiving sensitivity of the PS-16QAM is improved by 1.05dB compared with that of the uniform 16 QAM. Thus, the Probability Shaping (PS) technique effectively improves the sensitivity of the receiver.
As shown in fig. 7, a graph of the iteration number of the chaotic sequence of the computation time v.s in the chaotic encryption experiment shows the relationship between the computation time and the iteration number of the generated chaotic sequence. It can be seen that as the number of sequence iterations increases, the time consumed by the conventional iterative equation increases rapidly, while the time required by the variational self-encoder (VAE) remains around 0.2 ms. Therefore, compared with the chaos model of the traditional iterative equation, the chaos encryption model based on the variational self-encoder can shorten the calculation time and effectively reduce the complexity of the chaos encryption scheme.
Example two:
as shown in fig. 8, this embodiment provides an application of the chaos encryption method based on the variational self-encoder, and the chaos encryption method based on the variational self-encoder described in the first embodiment is used in an orthogonal frequency division multiplexing passive optical access communication system (OFDM-PON) to perform data encryption transmission.
A communication system includes:
the transmitting end is used for inputting an original data sequence, performing serial-parallel exchange, and mapping the original data sequence after serial-parallel exchange to a first chaotic sequence through quadrature amplitude modulation for phase covering; mapping the original data sequence after quadrature amplitude modulation to a second chaotic sequence through subcarrier modulation for frequency covering; converting the original data sequence modulated by the subcarrier from a frequency domain to a time domain through fast Fourier transform, and inputting the signals into an optical fiber after parallel-serial conversion;
and the receiving end is used for receiving the signal output to the optical fiber by the transmitting end and decrypting the signal, wherein the decryption process is the inverse transformation of the transmitting end. In the decryption process of quadrature amplitude demodulation and subcarrier demodulation, the chaos decryption sequence is generated by adopting the initial key set which is the same as that encrypted by the sending end so as to realize accurate decryption.
The invention introduces a depth generation model named a variational self-encoder to generate a chaotic sequence for encrypting OFDM symbols. By adopting training materials of different chaotic security schemes, the encoder can learn complex structures of data distribution in various chaotic models, and finally has the capacity of generating a large-space key group, thereby effectively improving the security of the OFDM-PON system. In addition, due to the parallel computation of the GPUs, the method required by the scheme only accounts for 1.38% of the conventional encryption scheme.
Example three:
the embodiment of the invention also provides computer equipment, which comprises a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the stored instructions to perform the steps of the method of:
obtaining an original chaotic sequence;
inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence;
carrying out phase covering encryption and frequency covering encryption on communication data according to the obtained reconstructed chaotic sequence;
the computer device provided in this embodiment may execute the chaos encryption method based on the variational self-encoder in embodiment 1, and the implementation principle and the technical effect are similar, which are not described herein again.
Example four:
an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the following method steps:
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the stored instructions to perform the steps of the method of:
obtaining an original chaotic sequence;
inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence;
carrying out phase covering encryption and frequency covering encryption on communication data according to the obtained reconstructed chaotic sequence;
the storage medium provided in this embodiment may implement the chaos encryption method based on the variational self-encoder in embodiment 1, and the implementation principle and the technical effect are similar, which are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A chaos encryption method based on a variational self-encoder is characterized by comprising the following steps:
the variational self-encoder model comprises an encoder network and a decoder network, wherein the encoder network comprises residual connecting blocks and self-attention layers which are alternately arranged, and the decoder network comprises convolutional layers and a loss layer arranged behind each convolutional layer;
the chaotic encryption method comprises the following steps:
obtaining an original chaotic sequence;
inputting the original chaotic sequence data into a pre-trained variational self-coder model for reconstruction processing, and outputting a reconstructed chaotic sequence;
carrying out phase covering encryption and frequency covering encryption on communication data according to the obtained reconstructed chaotic sequence;
the reconstruction chaotic sequence comprises a first chaotic sequence capable of carrying out phase covering on communication data and a second chaotic sequence capable of carrying out frequency covering on the communication data.
2. The chaotic encryption method based on the variational self-encoder according to claim 1, wherein the training method of the variational self-encoder model comprises the following steps:
acquiring an original sequence for training;
inputting the obtained original sequence into an encoder network for data encoding processing, and outputting a middle sequence with deviation from the original sequence, wherein the deviation of the middle sequence comprises a standard deviation and a mean vector;
and inputting the intermediate sequence into a decoder network for data decoding processing, performing iterative training by setting an adjustable training period to enable a model loss function to be converged, and outputting a reconstruction sequence to finish the training of the variational self-encoder model.
3. The chaotic encryption method based on the variational self-encoder according to claim 2, wherein the encoder network comprises 1 convolutional layer, 3 residual connection blocks and 2 self-attention layers;
the input original sequence is subjected to data compression processing through a convolutional layer, a ReLu function is adopted as an activation function, then dimension reduction processing is performed through 3 alternately arranged residual error connecting blocks and 2 self-attention layers, and finally a low-dimensional intermediate sequence is output.
4. The chaotic encryption method based on the variational self-encoder according to claim 3, wherein the convolution kernel size is 5 and the step size is 2.
5. The chaotic encryption method based on the variational self-encoder according to claim 3, wherein the decoder network comprises 2 convolution layers of 3 x 3, 2 batch normalization layers and 1 full connection layer, and a lost layer is connected after each convolution layer of 3 x 3;
the intermediate sequence output by the encoder network firstly passes through a 3 x 3 convolutional layer, a loss layer and a normalization layer, is processed by a ReLu activation function, then passes through the 3 x 3 convolutional layer, the loss layer and the normalization layer, is processed by a full connection layer, and outputs reconstruction training, and if the loss function of the model reaches a preset condition, the intermediate sequence data is directly used as the output of the decoder network.
6. The chaotic encryption method based on the variational self-encoder according to claim 5, wherein the convolution kernel size of the 3 x 3 convolutional layer is 1, and the loss rate of the lost layer is 0.2.
7. The chaotic encryption method based on the variational self-encoder according to claim 1, wherein the loss function is a minimum loss function, and the calculation formula comprises:
where σ is the standard deviation of the encoder network output; m is an average vector output by the encoder network; n is the data dimension of the original sequence input by the encoder network; i represents the ith value in the standard deviation vector; p is a radical of E (x | y) is the probability of outputting y when the encoder network input is x; p is a radical of D (y | x) is the probability of outputting x when the decoder network input is y.
8. An application of the chaos encryption method based on the variational self-encoder is characterized in that the chaos encryption method based on the variational self-encoder in any of claims 1-7 is used for an orthogonal frequency division multiplexing passive optical access communication system for data encryption transmission, and the communication system comprises:
the transmitting end is used for inputting an original data sequence, performing serial-parallel exchange, and mapping the original data sequence after serial-parallel exchange to a first chaotic sequence through quadrature amplitude modulation for phase covering; mapping the original data sequence after quadrature amplitude modulation to a second chaotic sequence through subcarrier modulation for frequency covering; converting the original data sequence modulated by the subcarrier from a frequency domain to a time domain through fast Fourier transform, and inputting the signals into an optical fiber after parallel-serial conversion;
and the receiving end is used for receiving the signal output to the optical fiber by the transmitting end and decrypting the signal, wherein the decryption process is the inverse transformation of the transmitting end.
9. A computer device comprising a processor and a storage medium;
the storage medium is used for storing instructions;
the processor is configured to operate in accordance with the instructions to perform the steps of the method according to any one of claims 1 to 7.
10. Computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466207.2A CN114915398A (en) | 2022-04-29 | 2022-04-29 | Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210466207.2A CN114915398A (en) | 2022-04-29 | 2022-04-29 | Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114915398A true CN114915398A (en) | 2022-08-16 |
Family
ID=82764304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210466207.2A Pending CN114915398A (en) | 2022-04-29 | 2022-04-29 | Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114915398A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115633129A (en) * | 2022-10-13 | 2023-01-20 | 同济大学 | Stack type sparse self-encoder and GAN chaotic sequence image encryption method and device |
| CN117434721A (en) * | 2023-11-22 | 2024-01-23 | 上海频准激光科技有限公司 | Optical fiber beam combination control method |
-
2022
- 2022-04-29 CN CN202210466207.2A patent/CN114915398A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115633129A (en) * | 2022-10-13 | 2023-01-20 | 同济大学 | Stack type sparse self-encoder and GAN chaotic sequence image encryption method and device |
| CN115633129B (en) * | 2022-10-13 | 2024-03-05 | 同济大学 | Stacked sparse self-encoder and GAN chaotic sequence image encryption method and device |
| CN117434721A (en) * | 2023-11-22 | 2024-01-23 | 上海频准激光科技有限公司 | Optical fiber beam combination control method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114915398A (en) | Variational self-encoder-based chaotic encryption method, application, computer equipment and storage medium | |
| CN112019321B (en) | Five-dimensional optical probability shaping encryption method based on high-dimensional chaotic system | |
| CN110677236B (en) | OFDM encryption method based on composite chaotic system and XOR operation | |
| CN105577359A (en) | OOFDM (Optical Orthogonal Frequency Division Multiplexing) encryption system based on chaos sequence pilot frequency mapping | |
| CN111464284B (en) | Three-dimensional optical probability shaping encryption method based on deep chaotic system | |
| CN112533199A (en) | OFDM channel physical key generation method and device based on USRP and computer equipment | |
| CN113810172B (en) | Low-redundancy encryption method and system for polarization code quantum noise stream physical layer | |
| CN106849963B (en) | Method and device for reducing peak-to-average power ratio of three-dimensional coherent light orthogonal frequency division multiplexing system | |
| CN111245596A (en) | Chaotic encryption method and system based on three-dimensional probability modeling | |
| Clegg et al. | A practical system for improved efficiency in frequency division multiplexed wireless networks | |
| Zhou et al. | Physical layer dynamic key encryption in OFDM-PON system based on cellular neural network | |
| CN114928435B (en) | Quantum noise stream encryption method and system based on DNA coding and SLM | |
| CN113904770A (en) | Quantum noise stream encryption key updating method and device and storage medium | |
| CN112583574B (en) | WFRFT transmission method and system based on two-dimensional chaotic mapping amplitude phase encryption | |
| CN113271201A (en) | Dynamic AES physical layer data encryption method | |
| CN114337849B (en) | Physical layer confidentiality method and system based on mutual information quantity estimation neural network | |
| CN114142987B (en) | OCDM system based on novel Logistic chaotic encryption mode | |
| CN115225249A (en) | MP-WFRFT communication method and system based on multi-cascade chaotic encryption | |
| Tang et al. | FBMC/OQAM security strategy based on diversity DNA encryption | |
| CN114302270A (en) | OFDM-PON physical layer encryption method and system based on multi-chaotic system and layered scrambling | |
| CN113644985A (en) | Ultra-long distance transmission method and system based on cellular automaton and DNA coding | |
| CN114615119A (en) | SCBT (sub-block binary tree) transmission method and system based on two-dimensional chaotic mapping constellation encryption | |
| Hussein Al-Delfi et al. | Hybrid Ciphering and Frequency Domain Scrambling for Secure Speech Transmission through MIMO-OFDM System. | |
| CN113949503B (en) | WFRFT (Wireless Fidelity-rft) secure communication method based on DNA dynamic coding | |
| Jabori et al. | Simple 2D chaotic remapping scheme for securing optical communication networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |