Optical shift encryption method and device

Abstract

The present application discloses an optical shift encryption method, apparatus, electronic device, and computer-readable storage medium. The method comprises: receiving encrypted data and a mask key, wherein the encrypted data is obtained by a sender performing an encryption operation on an image to be encrypted based on the mask key, wherein the encryption operation includes a random shift operation, the mask key can only be received by an authenticated user device, and only needs to be successfully received once if it has not been modified. The authenticated user device can receive the encrypted data multiple times via unicast or broadcast; obtaining a decoding network based on the mask key, wherein the decoding network is a semantically aware network trained based on a pre-set shift encryption protocol; and deciphering the encrypted data based on the decoding network to obtain semantic information. The present application can achieve high-precision and lightweight real-time deciphering of encrypted data.

Description

Technical Field

[0001] The present application relates to the field of computational photography, and in particular to an optical shift encryption method, device, electronic device, and computer-readable storage medium. Background Art

[0002] The theory of compressed sensing combines image acquisition and compression into one, greatly reducing the size and cost of the system and saving storage resources. The imaging system based on compressed sensing is based on single-photon detectors such as single pixels. It has a simple device and low requirements for imaging quality and hardware equipment. It can also be applied to non-visible light fields that traditional methods cannot capture. Moreover, the imaging method based on compressed sensing has shown significant advantages in storage and transmission methods, such as good encryption and extremely low information bandwidth. In terms of scene reconstruction, the imaging method based on compressed sensing is based on one-dimensional coupled data. On the one hand, traditional iterative methods such as alternating projection and conjugate gradient can be used to reconstruct high-dimensional scenes. On the other hand, deep learning technology can be used to build data sets and use neural networks such as convolutional neural networks and deep neural networks to achieve information reconstruction of the target scene.

[0003] In recent years, research has proposed information encryption methods based on compressed sensing. The basic idea is to treat the detected light field as the original information and the modulation mask as the key. A representative basic framework is as follows: the sender uses a series of structured light to modulate the target scene, broadcasting low-dimensional coupling data and transmitting the mask value to a specific receiver via an encrypted route. After receiving the corresponding plaintext and key information, the receiver can reconstruct the original text through traditional iterative methods to achieve information decryption. Unauthorized receivers who obtain the ciphertext data lack the corresponding key information and cannot decrypt it. This framework enables secure and reliable encryption based on compressed sensing. To further improve decoding efficiency, researchers have proposed various optimization methods, mainly including mask design optimization and the introduction of deep learning methods.

[0004] However, in the encryption mode of the above method, if the worst-case scenario occurs—that is, an attacker compromises the key information, the attacker and the recipient achieve information parity. The malicious attacker can then reconstruct the original image and decipher the ciphertext through traditional model-driven methods or data-driven deep learning methods. This situation is highly susceptible to information leakage, rendering the above method insecure. Furthermore, existing mask-modulated optical decoding methods only aim to reconstruct the scene, requiring further processing to extract the high-level semantic information of the original image. This computationally complex approach makes real-time decryption difficult.

[0005] Application Contents

[0006] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0007] To this end, the purpose of this application is to solve the problems of low security and difficulty in real-time decryption of existing information encryption methods based on compressed sensing. The first aspect of this application is to provide an optical shift encryption method, comprising:

[0008] receiving encrypted data and a mask key, wherein the encrypted data is obtained by a sender performing an encryption operation on an image to be encrypted based on the mask key, the encryption operation including a random shift operation;

[0009] Obtaining a decoding network based on the mask key, wherein the decoding network is a semantic perception network trained based on a preset shift encryption protocol;

[0010] The encrypted data is deciphered based on the decoding network to obtain semantic information.

[0011] In a possible embodiment, the encrypted data is obtained by the sender encoding and modulating the image to be encrypted according to the mask key, collecting coupling data corresponding to the image to be encrypted after the encoding and modulation, and randomly shifting the coupling data.

[0012] In a possible embodiment, obtaining a decoding network based on the mask key includes:

[0013] Constructing a low-dimensional coupled detection value dataset of the target scene according to a random shift strategy, wherein the dataset includes the mask key information;

[0014] Inputting the low-dimensional coupling detection value dataset into the semantic perception network, and outputting high-level semantic information of the target scene;

[0015] The semantic perception network is trained based on the high-level semantic information to obtain the decoding network.

[0016] In a possible embodiment, obtaining a decoding network based on the mask key includes:

[0017] Constructing a comparison table of the masking key and the decoding network, wherein the relationship between the masking key and the decoding network is one-to-one;

[0018] The corresponding decoding network is obtained according to the mask key based on the comparison table.

[0019] A second aspect of the present application is to provide an optical shift encryption device, comprising:

[0020] a receiving module, configured to receive encrypted data and a mask key, wherein the encrypted data is obtained by a sender performing an encryption operation on an image to be encrypted based on the mask key, the encryption operation including a random shift operation;

[0021] An acquisition module, configured to acquire a decoding network based on the mask key, wherein the decoding network is a semantic perception network trained based on a preset shift encryption protocol;

[0022] The decryption module is used to decrypt the encrypted data based on the decoding network to obtain semantic information.

[0023] In a possible embodiment, the encrypted data is obtained by the sender encoding and modulating the image to be encrypted according to the mask key, collecting coupling data corresponding to the image to be encrypted after the encoding and modulation, and randomly shifting the coupling data.

[0024] In a possible embodiment, the acquisition module includes:

[0025] A first construction unit is configured to construct a low-dimensional coupled detection value dataset of a target scene according to a random shift strategy, wherein the dataset includes mask key information;

[0026] An input-output unit, configured to input the low-dimensional coupling detection value dataset into the semantic perception network and output high-level semantic information of the target scene;

[0027] A training unit is used to train the semantic perception network based on the high-level semantic information to obtain the decoding network.

[0028] In a possible embodiment, the acquisition module includes:

[0029] A second construction unit is configured to construct a comparison table of the masking key and the decoding network, wherein the masking key and the decoding network have a one-to-one correspondence;

[0030] An acquiring unit is configured to acquire the corresponding decoding network according to the mask key based on the comparison table.

[0031] A third aspect of the present application is to provide an electronic device, comprising:

[0032] processor;

[0033] a memory for storing instructions executable by the processor;

[0034] The processor is configured to execute the instructions to implement the optical shift encryption method as described in any one of the first aspects.

[0035] A fourth aspect of the present application is to provide a computer-readable storage medium. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the optical shift encryption method as described in any one of the first aspects.

[0036] A fifth aspect of the present application is to provide a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the optical shift encryption method as described in any one of the first aspects is implemented.

[0037] Beneficial effects of this application:

[0038] In an embodiment of the present application, a decoding network is constructed by training a semantic perception network based on a pre-set shift encryption protocol to decipher encrypted data. The present application can achieve high-precision and lightweight real-time deciphering of encrypted data.

[0039] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0041] Figure 1 is a flow chart of an optical shift encryption method according to an embodiment of the present application;

[0042] Figure 2 Schematic diagram of the architecture of an optical shift encryption method according to an embodiment of the present application;

[0043] Figure 3 Graph showing decoding results of a simulated attack according to an embodiment of the present application;

[0044] Figure 4 Schematic diagram of the structure of an optical shift encryption device according to an embodiment of the present application;

[0045] Figure 5 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0046] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0047] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0048] Explanation of relevant terms:

[0049] Neural networks based on ultra-deep convolutional layers: A deep convolutional neural network that uses multiple very small convolution kernels throughout the network to combine them with the input on each pixel. Neural networks based on ultra-deep convolutional layers can be applied to a wide range of tasks and data sets, and their performance may be better than image processing methods built on lower-depth networks.

[0050] Neural Network Based on Composite Model Scaling: A recognition network based on a multi-dimensional hybrid model scaling method. This network takes into account both speed and accuracy, and is also one of the optimal network frameworks that simultaneously meets the three measurement indicators of network depth, network width, and image resolution.

[0051] The following describes the optical shift encryption method, device, electronic device and computer-readable storage medium proposed according to the embodiments of the present application with reference to the accompanying drawings. First, the optical shift encryption method proposed according to the embodiments of the present application will be described with reference to the accompanying drawings.

[0052] Figure 1 This is a flowchart of an optical shift encryption method according to an embodiment of the present application.

[0053] like Figure 1 As shown, the optical shift encryption method includes the following steps:

[0054] Step S110: receiving encrypted data and a mask key.

[0055] The encrypted data is obtained by the sender performing an encryption operation on the image to be encrypted based on the mask key, and the encryption operation includes a random shift operation.

[0056] In an embodiment of the present application, after the sender performs an encryption operation on the image to be encrypted based on the mask key to obtain encrypted data, the encrypted data and the mask key can be sent out, so that the receiver can receive the encrypted data and the mask key.

[0057] It should be noted that if Figure 2As shown in the figure, for masked keys, the sender can only send to designated recipients, i.e., authorized visitors (authenticated users), and if there is no change, it only needs to be sent once. For encrypted data, the sender can send it only to designated recipients or to the entire domain through broadcasting.

[0058] Step S120: Obtain a decoding network based on the mask key.

[0059] Among them, the decoding network is a semantic perception network trained based on a pre-set shift encryption protocol. The semantic perception network may include a neural network based on an ultra-deep convolutional layer and a neural network based on a composite model scaling method.

[0060] In an embodiment of the present application, after receiving the encrypted data and the mask key, the receiver can obtain a decoding network based on the mask key. There is a pre-set shift encryption protocol at the receiver, and the decoding network can be obtained by training a semantic perception network based on the pre-set shift encryption protocol.

[0061] It should be noted that in actual applications, due to the differences in perception accuracy, inference time, network scale, etc. among different semantic perception networks, the appropriate decoding network can be selected based on the reliability and real-time requirements of the specific encryption task, hardware resource conditions, etc.

[0062] Step S130: decrypt the encrypted data based on the decoding network to obtain semantic information.

[0063] In the embodiment of the present application, Figure 2 As shown, after the receiver obtains the decoding network based on the mask key, it can decrypt the encrypted data based on the decoding network to obtain semantic information.

[0064] In an embodiment of the present application, encrypted data and a masking key are received, a semantic-aware network is trained based on a pre-set shift encryption protocol to construct a decoding network, the decoding network is obtained based on the masking key, and the encrypted data is deciphered based on the decoding network to obtain semantic information. This application can achieve high-precision and lightweight real-time deciphering of encrypted data.

[0065] In a possible embodiment, the encrypted data is obtained by the sender encoding and modulating the image to be encrypted according to the mask key, collecting coupling data corresponding to the encoded and modulated image to be encrypted, and randomly shifting the coupling data.

[0066] In an embodiment of the present application, before sending the encrypted data and the mask key, the sender can encode and modulate the image to be encrypted according to the mask key, collect the coupling data corresponding to the image to be encrypted after encoding and modulation, and randomly shift the coupling data to obtain the encrypted data.

[0067] It should be noted that the mask key is designed based on a series of masks. Its function is to couple the two-dimensional light field image modulation into one-dimensional data to achieve data dimensionality reduction and information encryption. The types of series masks include but are not limited to random masks, Hadamard masks and network end-to-end optimized masks.

[0068] It should be noted that the sender can obtain encrypted data through physical detection devices or simulation software. To obtain encrypted data through a physical detection device: control a physical device such as a spatial light modulator to code and modulate the selected target, control a physical device such as a detector to collect the coded and modulated coupling data, thereby obtaining a series of coupling data corresponding to different codes, and control a physical device such as a shift register to randomly shift part of the coupling data to obtain a randomly shifted sequence of coupling data. The randomly shifted sequence of coupling data is the encrypted data. The detector can be a single-pixel detector, a bucket detector, or a digital micromirror. To obtain encrypted data through simulation software: perform Hadamard point multiplications on the selected target and a series of masks in sequence and sum them to obtain one-dimensional coupling data. Randomly shifting part of the one-dimensional coupling data yields the encrypted data.

[0069] In a possible embodiment, obtaining a decoding network based on a mask key includes:

[0070] Constructing a low-dimensional coupled detection value dataset of the target scene according to a random shift strategy, wherein the dataset includes mask key information;

[0071] Input the low-dimensional coupling detection value dataset into the semantic perception network and output high-level semantic information of the target scene;

[0072] The semantic perception network is trained based on high-level semantic information to obtain a decoding network.

[0073] In an embodiment of the present application, before obtaining a decoding network based on a mask key, the receiver can construct a low-dimensional coupling detection value dataset of the target scene according to a random shift strategy, wherein the dataset includes mask key information, input the low-dimensional coupling detection value dataset into a semantic perception network, output high-level semantic information of the target scene, and train the semantic perception network based on the high-level semantic information to obtain a decoding network.

[0074] It should be noted that the decoding network is a high-precision imaging-free perception network that only requires partial encrypted data as input and does not require image reconstruction. It outputs corresponding high-level semantic information.

[0075] In a possible embodiment, obtaining a decoding network based on a mask key includes:

[0076] Constructing a comparison table of masking keys and decoding networks, where the relationship between masking keys and decoding networks is one-to-one;

[0077] Obtain the corresponding decoding network according to the mask key based on the comparison table.

[0078] In an embodiment of the present application, the receiver can obtain different decoding networks based on different masking key training, so as to construct a comparison table of masking keys and decoding networks, wherein the relationship between masking keys and decoding networks is one-to-one corresponding. After receiving the encrypted data and masking key, the receiver can obtain the corresponding decoding network according to the masking key by querying the comparison table.

[0079] It should be noted that the specific implementation of the embodiment of the present application can prove that the optical shift encryption method provided by the present application has high security. By encrypting the MNIST (Mixed National Institute of Standards and Technology database) handwritten digit dataset, the dataset image size is 28*28, and the data volume of each one-dimensional measurement value is set to 78. At a sampling rate of 0.1, the network-optimized modulation mask is first obtained through end-to-end learning, and a shift dataset is constructed, where the training set is as high as 12,000 images. Secondly, based on a neural network network based on the composite model scaling method, a decoding network based on shift information is constructed. During the information transmission stage, the simulated ciphertext information randomly loses 1 to 3 values ​​and is randomly shifted, always ensuring that the length of the key and the ciphertext are consistent to achieve the effect of confusing attackers. If the recipient is an authorized user, it can obtain the decoding network described above by looking up the mask information or by an agreed construction method, and ultimately achieve a perception accuracy of 97.04%. When a hacker launches a malicious attack, consider the worst case scenario, that is, the attacker intercepts all the mask information. Figure 3The results of hackers deciphering the original text using traditional reconstruction methods are shown, where plaintext represents the original image, and TV, AP, etc. represent different decoding methods. Since the decoding key and the image information are not in sequence, the original image cannot be reconstructed. Similarly, the reconstruction method based on deep learning is also unable to decipher the ciphertext, showing that the optical shift encryption method proposed in this application has almost no possibility of information leakage. In addition, by simulating the situation where hackers use imaging-free perception networks to decipher the original image, in the worst case, the hackers intercepted all the mask information and constructed the corresponding decoding network, but because the mask does not match the original image, for this 10-classification task, the perception accuracy is only about 10%, which is equivalent to the network being unable to extract any feature information from the ciphertext, once again demonstrating the high security of the optical shift encryption method proposed in this application.

[0080] In order to implement the above embodiment, Figure 4 As shown, this embodiment further provides an optical shift encryption device 400 , which includes: a receiving module 410 , an acquiring module 420 , and a decrypting module 430 .

[0081] A receiving module 410 is configured to receive encrypted data and a mask key, wherein the encrypted data is obtained by the sender performing an encryption operation on the image to be encrypted based on the mask key, wherein the encryption operation includes a random shift operation;

[0082] An acquisition module 420 is configured to acquire a decoding network based on the mask key, wherein the decoding network is a semantic perception network trained based on a preset shift encryption protocol;

[0083] The decryption module 430 is used to decrypt the encrypted data based on the decoding network to obtain semantic information.

[0084] In a possible embodiment, the encrypted data is obtained by the sender encoding and modulating the image to be encrypted according to the mask key, collecting coupling data corresponding to the encoded and modulated image to be encrypted, and randomly shifting the coupling data.

[0085] In a possible embodiment, the acquisition module 420 includes:

[0086] A first construction unit is configured to construct a low-dimensional coupled detection value dataset of a target scene according to a random shift strategy, wherein the dataset includes mask key information;

[0087] Input-output unit, used to input the low-dimensional coupling detection value dataset into the semantic perception network and output high-level semantic information of the target scene;

[0088] The training unit is used to train the semantic perception network based on high-level semantic information to obtain a decoding network.

[0089] In a possible embodiment, the acquisition module 420 includes:

[0090] A second construction unit is used to construct a comparison table of mask keys and decoding networks, wherein the relationship between mask keys and decoding networks is one-to-one correspondence;

[0091] The acquisition unit is used to acquire the corresponding decoding network according to the mask key based on the comparison table.

[0092] The optical shift encryption device according to an embodiment of the present application receives encrypted data and a masking key, trains a semantic perception network based on a pre-set shift encryption protocol to construct a decoding network, obtains the decoding network based on the masking key, and decrypts the encrypted data using the decoding network to obtain semantic information. This application can achieve high-precision and lightweight real-time decryption of encrypted data.

[0093] It should be noted that the aforementioned explanation of the embodiment of the optical shift encryption method is also applicable to the optical shift encryption device of this embodiment, and will not be repeated here.

[0094] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a computer-readable storage medium, and a computer program product.

[0095] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device 500 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0096] like Figure 5 As shown, electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. Various programs and data required for the operation of device 500 can also be stored in RAM 503. Computing unit 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to bus 504.

[0097] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0098] The computing unit 501 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the optical shift encryption method. For example, in some embodiments, the optical shift encryption method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the optical shift encryption method described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform the optical shift encryption method by any other suitable means (e.g., by means of firmware).

[0099] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0100] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0101] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0102] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0103] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0104] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0105] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0106] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0107] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An optical shift encryption method, characterized in that: include: Receiving encrypted data and a mask key, wherein the encrypted data is obtained by a sender encoding and modulating an image to be encrypted based on the mask key, collecting coupled data corresponding to the image to be encrypted after the encoding and modulation, and randomly shifting a portion of the coupled data; Acquire a decoding network based on the mask key, wherein the decoding network is a semantic perception network trained based on a preset shift encryption protocol, and the decoding network is an imaging-free perception network; deciphering the encrypted data based on the decoding network to obtain semantic information; Wherein, obtaining a decoding network based on the mask key includes: Constructing a low-dimensional coupled detection value dataset of the target scene according to a random shift strategy, wherein the dataset includes the mask key information; Inputting the low-dimensional coupling detection value dataset into the semantic perception network, and outputting high-level semantic information of the target scene; The semantic perception network is trained based on the high-level semantic information to obtain the decoding network.

2. The method according to claim 1, characterized in that The obtaining of a decoding network based on the mask key includes: Constructing a comparison table of the masking key and the decoding network, wherein the relationship between the masking key and the decoding network is one-to-one; The corresponding decoding network is obtained according to the mask key based on the comparison table.

3. An optical shift encryption device, characterized in that: include: a receiving module, configured to receive encrypted data and a masking key, wherein the encrypted data is obtained by a sender encoding and modulating an image to be encrypted based on the masking key, collecting coupled data corresponding to the encoded and modulated image to be encrypted, and randomly shifting a portion of the coupled data; An acquisition module, configured to acquire a decoding network based on the mask key, wherein the decoding network is a semantic perception network trained based on a preset shift encryption protocol, and the decoding network is an imaging-free perception network; A decryption module, configured to decrypt the encrypted data based on the decoding network to obtain semantic information; Wherein, the acquisition module includes: A first construction unit is configured to construct a low-dimensional coupled detection value dataset of a target scene according to a random shift strategy, wherein the dataset includes mask key information; An input-output unit, configured to input the low-dimensional coupling detection value dataset into the semantic perception network and output high-level semantic information of the target scene; A training unit is used to train the semantic perception network based on the high-level semantic information to obtain the decoding network.

4. The device according to claim 3, characterized in that The acquisition module includes: A second construction unit is configured to construct a comparison table of the masking key and the decoding network, wherein the masking key and the decoding network have a one-to-one correspondence; An acquiring unit is configured to acquire the corresponding decoding network according to the mask key based on the comparison table.

5. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the optical shift encryption method according to any one of claims 1 to 2.

6. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the optical shift encryption method according to any one of claims 1 to 2.

Images