A method and device for encrypting potential secret images in a port, and a medium

Abstract

This invention discloses a method, device, and medium for encrypting potentially classified port images, belonging to the field of image encryption technology. It addresses the technical problem that sensitive information in existing port images is easily exposed to potential attack risks, and that traditional port image encryption methods have certain limitations and cannot provide sufficient security. The method includes: transforming the input classified port image into a matrix of channel pixels to obtain a one-dimensional matrix of channel pixels; scrambling the one-dimensional matrix of channel pixels to obtain random pixel arrangements; weakening the strong correlation features of the random pixel arrangements to obtain an initialization key for the classified port image; performing iterative optimization and evaluation on the initialization key based on the global optimal position and global optimal value of relevant local contours to obtain an optimal key; and obtaining an encrypted port image under a mask DNA encoding scheme.

Description

Technical Field

[0001] This application relates to the field of image encryption, and in particular to a method, device and medium for encrypting potentially classified images of a port. Background Technology

[0002] With the rapid development of multimedia and information technologies, the internet has become a major channel for communication. However, while enjoying the convenience of information transmission, sensitive information contained in port images, such as geographical coordinates, wharf layouts, and ship operation dynamics, is also exposed to potential attack risks.

[0003] Compared to traditional information, digital images have a larger data volume and stronger correlation between adjacent pixels, making conventional block ciphers or stream encryption algorithms often insufficient to provide adequate security for large-sized, strongly correlated port images. Chaotic systems, as an important branch of nonlinear dynamics, possess many prominent cryptographic characteristics such as pseudo-randomness and ergodicity. Therefore, chaotic systems are widely used in image encryption. The purpose of image encryption using chaotic systems is to scramble the arrangement of image pixels to obtain an image with low correlation, making the pattern features of the original image invisible to the naked eye. Swarm intelligence algorithms are often used for convex optimization, and their principles precisely meet the goal of obtaining low correlation in image encryption. Summary of the Invention

[0004] This application provides a method, device, and medium for encrypting potentially classified port images to address the following technical problems: sensitive information in existing port images is easily exposed to potential attack risks, and traditional port image encryption methods have certain limitations and cannot provide sufficient security.

[0005] The embodiments of this application adopt the following technical solutions:

[0006] On one hand, embodiments of this application provide a method, device, and medium for encrypting potentially classified images of a port, including: performing a matrix transformation of channel pixels on an input classified port image to obtain a one-dimensional matrix of channel pixels; shuffling the image pixels of the one-dimensional matrix of channel pixels using a Logistic chaotic sequence to obtain random pixel permutations; weakening the strong correlation features of the random pixel permutations according to a preset applicability function to obtain an initialization key for the classified port image; performing an optimization iterative evaluation process on the initialization key using a proxy-assisted quasi-affine marine predator algorithm to optimize the global optimal position and global optimal value of the local contours to obtain an optimal key; and obtaining an encrypted port image under a mask DNA encoding scheme based on the optimal key.

[0007] This application's embodiments construct a defense-in-depth system through triple protection: chaotic initial scrambling, intelligent optimization of strong keys, and DNA encoding. Furthermore, the keys can be dynamically generated, with each image having its own unique key, resulting in extremely strong resistance to attacks. It can effectively resist statistical attacks, differential attacks, known-plaintext attacks, and brute-force attacks. Moreover, the encrypted image exhibits extremely low pixel correlation and high information entropy, indistinguishable from random noise, achieving excellent encryption results from an information theory perspective. Simultaneously, combining the latest Ocean Predator algorithm with chaotic cryptography transforms the encryption process from a fixed procedure to intelligent optimization, representing a cutting-edge development direction in the field of image encryption.

[0008] In one feasible implementation, the input port classified image is subjected to a matrix transformation of channel pixels to obtain a one-dimensional channel pixel matrix. Specifically, this includes: decomposing the port classified image under channel pixel color to obtain three two-dimensional pixel matrices; wherein the channel pixel colors include red, green, and blue; and transforming all the two-dimensional pixel matrices into one-dimensional matrices to obtain the one-dimensional channel pixel matrix.

[0009] In one feasible implementation, the image pixels of the one-dimensional matrix of channel pixels are shuffled using a Logistic chaotic sequence to obtain random pixel permutations and combinations. Specifically, this includes: using the Chen hyperchaotic system parameters and the Logistic chaotic sequence to randomly shuffle the pixel feature parameters in the one-dimensional matrix of channel pixels to obtain random pixel permutations and combinations, and obtaining the random pixel permutations and combinations based on the Logistic chaotic mapping.

[0010] In one feasible implementation, before iteratively weakening the strong correlation features of the random pixel permutations and combinations according to a preset applicability function to obtain the initialization key for the port classified image, the method further includes: according to The correlation coefficients of the three-channel pixels in the classified port image were obtained. ;in, and These are adjacent data values ​​in the classified port image; Represents a randomly selected pixel from the random pixel permutations; i is a mathematical constant; according to The suitability for encrypting the classified images of the port is obtained. ;in, The correlation coefficient for the red channel; The correlation coefficient for the green channel; The correlation coefficient for the blue channel; the applicability The functional framework is an applicability function.

[0011] In one feasible implementation, the strong correlation features of the random pixel permutations and combinations are weakened according to a preset applicability function to obtain the initialization key of the port classified image. Specifically, this includes: weakening the strong correlation features of the random pixel permutations and combinations of the port classified image through the applicability of three-channel pixels, and performing encryption calculations on the port classified image through the Chen hyperchaotic system to obtain the initialization key used for encryption processing of the port classified image.

[0012] In one feasible implementation, before optimizing the initialization key using a proxy-assisted quasi-affine marine predator algorithm to obtain the optimal key by assessing the global optimal position and value of the local contour, the method further includes: performing algorithmic hybridization processing between the quasi-affine optimization algorithm and the marine predator strategy, including: initializing the particle population and obtaining an initial solution; updating the optimal solution obtained by evaluating the initial fitness value with the phased optimal solution position update processing related to the co-evolution matrix and the current iteration number to obtain a new optimal solution; transforming the new optimal solution using a quasi-affine transformation, and based on the evaluated result... The new fitness value is obtained to complete the algorithm hybridization process of the quasi-affine marine predator algorithm; according to the auxiliary agent strategy, the radial basis network is added to the quasi-affine marine predator algorithm to obtain the agent-assisted quasi-affine marine predator algorithm, including: initializing the population; constructing the auxiliary agent model; finding the local optimum of the particles and updating the auxiliary agent model through the quasi-affine marine predator algorithm; updating the latest population position and fitness value, selecting the best particles that are better than themselves and updating the historical database; updating the global optimum position and global optimum value until the algorithm ends, to obtain the agent-assisted quasi-affine marine predator algorithm.

[0013] In one feasible implementation, the initialization key is optimized and evaluated for the global optimal position and global optimal value of the local contour using a proxy-assisted quasi-affine marine predator algorithm to obtain the optimal key. Specifically, this includes: using a proxy-assisted quasi-affine marine predator algorithm and based on an applicability function, solving for the global optimal position and global optimal value of the local contour using the initialization key to obtain a number of solution results; using an initialized Chen hyperchaotic system, iteratively evaluating each solution result, and obtaining the optimal key for optimal encryption of the port confidential image based on the weakest correlation coefficient of the three-channel pixel correlation coefficient.

[0014] In one feasible implementation, based on the optimal key, an encrypted port image under a mask DNA encoding scheme is obtained, specifically including: determining the mask DNA encoding scheme for image encryption processing based on the optimal key; and performing DNA encryption processing on the current classified port image under a Chen hyperchaotic system using the mask DNA encoding scheme to obtain the encrypted port image.

[0015] Secondly, embodiments of this application also provide an encryption processing device for potentially classified port images, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to execute an encryption processing method for potentially classified port images as described in any of the above embodiments.

[0016] Thirdly, embodiments of this application also provide a non-volatile computer storage medium, which is a non-volatile computer-readable storage medium storing at least one program, each program including instructions, which, when executed by a terminal, cause the terminal to perform an encryption processing method for a potentially classified port image as described in any of the above embodiments.

[0017] This application provides a method, device, and medium for encrypting potentially classified images of ports. Compared with the prior art, the embodiments of this application have the following beneficial technical effects:

[0018] 1. Enhanced security: By using chaotic sequences to scramble image pixels, the difficulty of cracking the image is increased, thereby improving the security of classified images.

[0019] 2. Algorithm complexity: The algorithm employs a Logistic chaotic sequence and a surrogate-assisted quasi-affine ocean predator algorithm, which provides a relatively complex encryption process, making it difficult for crackers to find the encryption and decryption patterns.

[0020] 3. Weakening of strong correlation: By weakening the strong correlation of random pixel permutations and combinations through a newly constructed applicability function, the encrypted image can be made more difficult to be attacked by statistical analysis.

[0021] 4. Initialization Key Optimization: The initialization key is optimized using a proxy-assisted quasi-affine ocean predator algorithm, which ensures that the key has high randomness and complexity, further enhancing the security of encryption.

[0022] 5. Local contour protection: The algorithm considers the optimization of the global optimal position and global optimal value of local contours, which helps to protect the key information structure in the image so that it will not be lost even during the encryption process.

[0023] 6. Encryption efficiency: Through algorithm optimization, encryption efficiency can be improved while ensuring security.

[0024] 7. Wide applicability: This scheme can be applied to the encryption of classified images in different types of ports, and has a wide range of applicability. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0026] Figure 1 A flowchart illustrating an encryption method for potentially classified images of a port, provided in this application embodiment;

[0027] Figure 2 A flowchart of an optimized encryption algorithm for potentially classified images of a port is provided as an embodiment of this application.

[0028] Figure 3 This is a schematic diagram of the structure of an encryption processing device for potentially classified images of a port, provided as an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0030] This application provides an encryption processing method for potentially classified images of a port, such as... Figure 1 As shown, the encryption method for potentially classified images of a port specifically includes steps S101-S105:

[0031] S101. Perform a matrix transformation on the input port classified image to obtain a one-dimensional matrix of channel pixels.

[0032] Specifically, the classified port images are first decomposed using channel pixel colors to obtain three two-dimensional pixel matrices. The channel pixel colors include red, green, and blue.

[0033] Furthermore, all the two-dimensional pixel matrices are transformed into one-dimensional matrices to obtain the one-dimensional matrix of channel pixels.

[0034] In one embodiment, Figure 2 A flowchart of an optimized encryption algorithm for potentially classified images of a port, as provided in this application embodiment, is shown below. Figure 2 As shown, let the input color image be... It is decomposed into three two-dimensional pixel matrices, R (red), G (green), and B (blue), and further transformed into a one-dimensional matrix: in, , , These are the pixels of the three channels of the image.

[0035] S102. Using the Logistic chaotic sequence, the one-dimensional matrix of channel pixels is shuffled to obtain random pixel permutations and combinations.

[0036] Specifically, the pixel feature parameters in the one-dimensional matrix of channel pixels can be randomly shuffled by using the Chen hyperchaotic system parameters and the Logistic chaotic sequence, and random pixel permutations and combinations can be obtained based on the Logistic chaotic mapping.

[0037] In one embodiment, the initialization key is the Chen hyperchaotic system parameter. and logistic chaotic sequences The image pixels are first shuffled using a logistic chaotic sequence to enhance the randomness of pixel arrangement. (The parameters of the hyperchaotic system are then described.) Generated by an optimization algorithm. Examples of chaotic logistics sequences include: ,in, ,when When the Lyapunov exponent is greater than 0, the system is in a completely chaotic state. The Logistic chaotic map is the most classic chaotic map, and its bifurcation graph is often referred to as the "worm mouth model".

[0038] As a feasible implementation method, a hyperchaotic system is generally defined as a system of differential equations with four or more dimensions, and having at least two or more positive Lyapunov exponents. Examples include: ,in, All of these are system state variables. These are the system's control parameters.

[0039] S103. Based on the preset applicability function, the strong correlation features of random pixel permutations and combinations are weakened to obtain the initialization key for the port classified image.

[0040] Specifically, adjacent pixels in natural images exhibit strong correlation characteristics in the horizontal, vertical, and diagonal directions, and effective encryption algorithms should significantly reduce this correlation. This paper constructs a novel applicability function for color image encryption, employing a three-channel pixel correlation coefficient (...). As shown below, to make the encrypted image Get as close to 0 as possible.

[0041] Furthermore, according to The correlation coefficients of the three-channel pixels in the classified port image were obtained. .in, and For adjacent data values ​​in classified port images; represents a randomly selected pixel from a random pixel permutation; i is a mathematical constant.

[0042] Furthermore, according to The applicability of encrypting classified images of ports was obtained. .in, The correlation coefficient for the red channel; The correlation coefficient for the green channel; The correlation coefficient for the blue channel; applicability. The functional framework is an applicability function.

[0043] Furthermore, such as Figure 2 As shown, the strong correlation features of random pixel arrangement and combination in the port classified image are weakened by the applicability of the three-channel pixels, and the port classified image is encrypted by the Chen hyperchaotic system to obtain the initialization key for the encryption processing of the port classified image.

[0044] S104. Using a proxy-assisted quasi-affine marine predator algorithm, the initialization key is evaluated iteratively by optimizing the global optimal position and global optimal value of the local contour to obtain the optimal key.

[0045] It should be noted that the Quasi-Affine Transformation Algorithm (QUATRE) is a co-evolutionary algorithm based on quasi-affine transformations. Its unique structure addresses the bias problem inherent in Differential Evolution (DE). Affine transformation, a term in geometry, describes the process of transforming two vectors from one affine space to another. The algorithm has a simple structure, retaining only a mutation strategy similar to DE. First, QUTAER needs to initialize a set of... Random solutions, such as: in, , These are the upper and lower bounds of the variable, respectively. It belongs to The initial population is uniformly distributed. Subsequently, the initial population is divided into groups based on an evaluation fitness function. predators and Prey, i.e., the initial population position. Afterwards, the population follows the formula: Perform iterations, where, It is the globally optimal position. This indicates term-by-term multiplication. It is a vector generated by random permutation. It is a constant. It guides the iteration method of the evolution matrix. It is a co-evolutionary matrix. Yes Find the inverse of all elements.

[0046] Specifically, the quasi-affine optimization algorithm needs to be hybridized with the marine predator strategy. This process includes: first, initializing the particle population and obtaining an initial solution; then, updating the optimal solution obtained from the initial fitness value evaluation by updating the position of the optimal solution in stages with respect to the co-evolutionary matrix and the current iteration number, resulting in a new optimal solution; finally, applying a quasi-affine transformation to the new optimal solution, and completing the hybridization process of the quasi-affine marine predator algorithm based on the new fitness value obtained after evaluation.

[0047] As a feasible implementation method, the marine predator algorithm has a complex structure, and the eddy current and fish aggregator (FAD) strategies can significantly hinder the predator's exploration process, causing it to get stuck in local optima. The quasi-affine algorithm's cruise strategy can effectively improve this problem and enhance global exploration capabilities. Therefore, this application hybridizes the quasi-affine optimization algorithm with the marine predator strategy, proposing a quasi-affine marine predator algorithm (QUATRE hybrid Marine PredatorsAlgorithm, Qt-MPA). The specific steps are as follows:

[0048] 1) Initialize the population and generate a set The initial solution.

[0049] 2) Using the initial fitness value, evaluate a set of elite solutions (optimal solutions), denoted as . The remaining matrices are denoted as .

[0050] 3) Generate a co-evolutionary matrix and .

[0051] 4) Update the optimal solution position in stages based on the current iteration number, and return the new position. and .

[0052] 5) Use quasi-affine transformation to... Perform the transformation as follows: .

[0053] 6) Evaluate and obtain new applicability values ​​and If the new fitness value is better than the previous generation's optimal value, then .

[0054] Furthermore, a radial basis function network can be incorporated into the quasi-affine marine predator algorithm based on an auxiliary agent strategy, resulting in an agent-assisted quasi-affine marine predator algorithm. This algorithm includes: first, initializing the population; then, constructing an auxiliary agent model; next, using the quasi-affine marine predator algorithm to find local optima for particles and updating the auxiliary agent model; then, updating the latest population position and fitness value, selecting the best particles superior to themselves, and updating the historical database; finally, updating the global optimum position and global optimum value until the algorithm terminates, thus obtaining the agent-assisted quasi-affine marine predator algorithm.

[0055] Furthermore, using a proxy-assisted quasi-affine marine predator algorithm and based on the applicability function, the initialization key is processed to solve for the global optimal position and global optimal value of the local contour, resulting in a number of solution iterations.

[0056] As a feasible implementation method, although using quasi-affine optimization algorithms can improve the global exploration capabilities of marine predators, it often fails to delve deeply into local exploration when faced with expensive problems. Therefore, this application utilizes the idea of ​​an auxiliary surrogate, incorporating a Radial Basis Function (RBF) network into the algorithm's local exploration. The RBF is used to fit the optimal value. The main purpose of using a surrogate model to assist the evolutionary algorithm is to better grasp the local contours of the problem and find a better solution with the same computational cost, compared to using an evolutionary algorithm alone. The Surogate-assisted QUATRE hybrid Marine Predators Algorithm (SQTMPA) consists of four main parts: initializing the population, constructing an RBF surrogate model, using the QUATRE algorithm to find local optima and updating the surrogate model, and updating the population position and fitness value. The specific steps are as follows:

[0057] Step 1: Initialize sample points and the mean of the expensive problem suitability function using Latin hypercube and store them in... Historical database.

[0058] Step 2: Select from the current database The optimal particle position is used to initialize or reinitialize the evolutionary population of SQTMPA.

[0059] Step 3: Store all in The RBF model is trained using sample points to obtain the RBF model.

[0060] Step 4: Find the optimal solution of the RBF model through Qt-MPA sampling, evaluate its fitness value using an accurate fitness function, and save it to the archive.

[0061] Step 5: If before If the best non-repeating sample has changed, then update the RBF model.

[0062] Step 6: Using the above formula: This generates a new global position.

[0063] Step 7: Use RBF to re-estimate the fitness value of each particle, select new optimal particles that are better than themselves, and update the results. .

[0064] Step 8: Update the global optimal position and global optimal value until the algorithm ends.

[0065] Furthermore, such as Figure 2As shown, the initial Chen hyperchaotic system is used to iteratively evaluate the solution results for each iteration, and the optimal key for encrypting the classified port images is obtained based on the weakest correlation of the correlation coefficients of the three-channel pixels. In other words, after the Chen hyperchaotic system calculates the initial key, the optimal key is determined by evaluating the information entropy using a proxy-assisted quasi-affine ocean predator algorithm.

[0066] S105. Based on the optimal key, obtain the encrypted port image under the masked DNA encoding scheme.

[0067] Specifically, a mask DNA encoding scheme for image encryption processing needs to be determined based on the optimal key. Finally, using the mask DNA encoding scheme, DNA encryption processing under a Chen hyperchaotic system is performed on the current classified port image to obtain an encrypted port image.

[0068] In one embodiment, such as Figure 2 As shown, the novel fitness function constructed in this application will be solved using an intelligent optimization algorithm, meaning that the hyperchaotic system initialized in each solution will pass the evaluation in each iteration. That is, it combines the correlation coefficients of three-channel pixels in the classified port image. : Applicability to encrypt classified images in ports : The pseudo-radiative oceanic predator algorithm, aided by an agent, updates the solution by calculating the information entropy and correlation of the solution. A hyperchaotic system is initialized in each solution iteration. Each iteration is evaluated, and finally, the optimal result is obtained. , All by The obtained solution serves as the mask DNA encoding scheme. Then, using this mask DNA encoding scheme, the current classified port image is subjected to DNA encryption processing under a Chen hyperchaotic system to obtain an encrypted port image.

[0069] In DNA encoding, the four deoxyribonucleotides that make up DNA are adenine (A), cytosine (C), guanine (G), and thymidine (T). The complementary base pairing principle of DNA is similar to the complementary relationship between 0 and 1 in the binary system. For binary numbers, 00 and 11, and 01 and 10 are complementary. In the encryption process, the key is generated by a hyperchaotic system and used to control the DNA encoding rules to achieve the purpose of random encoding.

[0070] As a feasible implementation method, when it is necessary to decrypt the encrypted port image later, the decryption process is the reverse operation of the encryption, and the same key used for encryption must be used to decrypt the original image.

[0071] In addition, embodiments of this application also provide an encryption processing device for potentially classified images of ports, such as... Figure 3 As shown, the encryption processing device 300 for potentially classified images of the port specifically includes:

[0072] At least one processor 301; and a memory 302 communicatively connected to the at least one processor 301; wherein the memory 302 stores instructions executable by the at least one processor 301 to enable the at least one processor 301 to execute:

[0073] The input port classified image is transformed into a matrix of channel pixels to obtain a one-dimensional matrix of channel pixels.

[0074] By using the Logistic chaotic sequence, the one-dimensional matrix of channel pixels is shuffled to obtain random pixel permutations and combinations.

[0075] Based on the preset applicability function, the strong correlation features of random pixel permutations and combinations are weakened to obtain the initialization key for the port classified image.

[0076] By using a proxy-assisted quasi-affine marine predator algorithm, the initialization key is evaluated iteratively by optimizing the global optimal position and global optimal value of the local contour, and the optimal key is obtained.

[0077] Based on the optimal key, an encrypted port image under the masked DNA encoding scheme is obtained.

[0078] This application's embodiments construct a defense-in-depth system through triple protection: chaotic initial scrambling, intelligent optimization of strong keys, and DNA encoding. Furthermore, the keys can be dynamically generated, with each image having its own unique key, resulting in extremely strong resistance to attacks. It can effectively resist statistical attacks, differential attacks, known-plaintext attacks, and brute-force attacks. Moreover, the encrypted image exhibits extremely low pixel correlation and high information entropy, indistinguishable from random noise, achieving excellent encryption results from an information theory perspective. Simultaneously, combining the latest Ocean Predator algorithm with cryptography transforms the encryption process from a fixed procedure to intelligent optimization, representing a cutting-edge development direction in the field of image encryption.

[0079] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the description of the method embodiments.

[0080] The devices and media provided in this application are one-to-one with the methods. Therefore, the devices and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0081] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can 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, etc.) containing computer-usable program code.

[0082] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0087] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0088] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0089] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of this specification.

Claims

1. A method for encrypting potentially classified images of a port, characterized in that, The method includes: The input port classified image is transformed into a matrix of channel pixels to obtain a one-dimensional matrix of channel pixels. The image pixels of the one-dimensional matrix of channel pixels are shuffled using a Logistic chaotic sequence to obtain random pixel permutations and combinations. according to The correlation coefficients of the three-channel pixels in the classified port image were obtained. ;in, and These are adjacent data values ​​in the classified port image; represents a pixel randomly selected from the random pixel permutation and combination; i is a mathematical constant; according to The suitability for encrypting the classified images of the port is obtained. ;in, The correlation coefficient for the red channel; The correlation coefficient for the green channel; The correlation coefficient for the blue channel; the applicability The functional framework is an applicability function; Based on a preset applicability function, the strong correlation features of the random pixel permutation and combination are weakened to obtain the initialization key of the port classified image. The initialization key is evaluated iteratively by using a proxy-assisted quasi-affine marine predator algorithm to optimize the global optimal position and global optimal value of the local contour, thereby obtaining the optimal key. Based on the optimal key, an encrypted port image under the masked DNA encoding scheme is obtained.

2. The encryption processing method for potentially classified port images according to claim 1, characterized in that, The input port classified image is transformed into a matrix of channel pixels to obtain a one-dimensional matrix of channel pixels, specifically including: The classified port image is decomposed using channel pixel color to obtain three two-dimensional pixel matrices; wherein the channel pixel colors include: red, green and blue; The two-dimensional pixel matrix is ​​transformed into a one-dimensional matrix to obtain the channel pixel one-dimensional matrix.

3. The encryption processing method for potentially classified port images according to claim 1, characterized in that, The image pixels of the one-dimensional matrix of channel pixels are shuffled using a Logistic chaotic sequence to obtain random pixel permutations and combinations, specifically including: Using the Chen hyperchaotic system parameters and the Logistic chaotic sequence, the pixel feature parameters in the one-dimensional matrix of channel pixels are randomly shuffled to create a random pixel arrangement, and the random pixel arrangement is obtained based on the Logistic chaotic mapping.

4. The encryption processing method for potentially classified port images according to claim 1, characterized in that, Based on a preset applicability function, the strong correlation features of the random pixel permutations are weakened to obtain the initialization key for the port classified image, specifically including: By utilizing the applicability of three-channel pixels, the strong correlation characteristics of random pixel arrangements in the port classified image are weakened. Then, the port classified image is encrypted using the Chen hyperchaotic system to obtain the initialization key used for encrypting the port classified image.

5. The encryption processing method for potentially classified port images according to claim 1, characterized in that, Before obtaining the optimal key by performing optimization evaluation on the initialization key regarding the global optimal position and global optimal value of the local contour using a proxy-assisted quasi-affine marine predator algorithm, the method further includes: The quasi-affine optimization algorithm is hybridized with the marine predator strategy, including: Initialize the particle population and derive an initial solution; The optimal solution evaluated by the initial fitness value is updated with the relevant co-evolutionary matrix and the position of the optimal solution in stages under the current iteration number to obtain a new optimal solution; The new optimal solution is transformed using a quasi-affine transformation, and the algorithm hybridization process of the quasi-affine marine predator algorithm is completed based on the new fitness value obtained after evaluation. Based on the assisted agent strategy, a radial basis function network is added to the quasi-affine marine predator algorithm to obtain an agent-assisted quasi-affine marine predator algorithm, including: Initialize the population; Build an auxiliary agent model; The local optimum of the particle is found and the auxiliary agent model is updated using the quasi-affine ocean predator algorithm. Update the latest population position and fitness value, select the best particles that are superior to themselves, and update the historical database; Update the global optimal position and global optimal value until the algorithm ends, and obtain the surrogate-assisted quasi-affine marine predator algorithm.

6. The encryption processing method for potentially classified port images according to claim 1, characterized in that, The initialization key is optimized by using a proxy-assisted quasi-affine marine predator algorithm to evaluate the global optimal position and global optimal value of the local contour, resulting in the optimal key. Specifically, this includes: By using a proxy-assisted quasi-affine marine predator algorithm and based on the applicability function, the initialization key is processed to solve for the global optimal position and global optimal value of the local contour, resulting in a number of solution operations. The solution results are iteratively evaluated using the initialized Chen hyperchaotic system, and the optimal key for optimal encryption of the port classified image is obtained based on the weakest correlation of the correlation coefficients of the three-channel pixels.

7. The encryption processing method for potentially classified port images according to claim 1, characterized in that, Based on the optimal key, an encrypted port image under the masked DNA encoding scheme is obtained, specifically including: Based on the optimal key, the mask DNA encoding scheme for image encryption processing is determined; Using the mask DNA encoding scheme, the current classified port image is subjected to DNA encryption processing under the relevant Chen hyperchaotic system to obtain the encrypted port image.

8. An encryption processing device for potentially classified images of a port, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor to enable the at least one processor to perform an encryption processing method for a potentially classified port image according to any one of claims 1-7.

9. A non-volatile computer storage medium, characterized in that, The storage medium is a non-volatile computer-readable storage medium that stores at least one program, each program including instructions that, when executed by a terminal, cause the terminal to perform an encryption processing method for potentially classified images of a port according to any one of claims 1-7.

Images