Privacy protection calculation method and system for hyperspectral remote sensing image data

Abstract

The invention relates to the technical field of data security, in particular to a privacy protection computing method and system for hyperspectral remote sensing image data, and the method comprises the steps: a key management center generates an index set as a key, and transmits the key to user computing equipment through a secure channel; the user computing device carries out corresponding encryption computing on the hyperspectral remote sensing image matrix by adopting the key sent by the key management center according to different privacy protection computing schemes needing to be executed, and sends encrypted data to the cloud server; the cloud server performs corresponding privacy protection calculation on the encrypted data according to different privacy protection calculation schemes needing to be executed, and returns a calculation result to the user calculation equipment; the user computing device verifies and decrypts the computing result in a corresponding mode according to different privacy protection computing schemes needing to be executed, and a final computing result is obtained. According to the invention, the encryption and decryption efficiency of the hyperspectral remote sensing image can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data security technology, and more specifically to a privacy protection calculation method and system for hyperspectral remote sensing image data. Background Art

[0002] Hyperspectral remote sensing image data plays an important role in application fields such as geographic information mapping, environmental monitoring, land resource survey, and agricultural monitoring. With the development of ground object image acquisition technology, hyperspectral remote sensing technology uses hyperspectral images containing more than 100 spectral band information to achieve accurate remote sensing analysis. Each pixel point of a hyperspectral image has rich spatial, radiation, and spectral information, and can show many response characteristics of ground objects to electromagnetic waves. Generally, in the hyperspectral remote sensing process, the image is processed into a high-dimensional matrix. Machine learning algorithms for remote sensing analysis such as feature selection, anomaly detection, and object recognition can use high-dimensional pixel feature vectors to extract significant target features, thereby achieving accurate analysis and prediction of ground object information.

[0003] Based on the characteristics of hyperspectral image data, large-scale matrix operations, such as image filtering convolution operations and matrix multiplication in vector dimension reduction principal component analysis algorithms, image fitting least squares methods, and matrix pseudo-inverse operations in feature selection sparse representation algorithms, play an important role in performing hyperspectral remote sensing tasks. However, while a large amount of spectral band data provides rich information for remote sensing analysis, the operation of large-scale hyperspectral image matrices brings a heavy computational burden to user computing devices.

[0004] At present, collaborating with cloud servers to complete complex computing tasks is an effective solution for realizing hyperspectral remote sensing analysis. By sending computing tasks with high computing power requirements to cloud servers with stronger computing power for privacy-preserving computing, the difficulty of local hyperspectral remote sensing analysis can be effectively reduced on the basis of ensuring data security. At present, machine learning solutions based on cloud computing widely use various privacy protection methods to ensure the confidentiality, integrity, and availability of data during the calculation process. Among them, the privacy-preserving computing method based on matrix blinding has the advantages of high efficiency and low resource consumption, and is more suitable for machine learning tasks such as remote sensing analysis with real-time feedback requirements. The matrix blinding method usually uses a specially designed matrix as the key, and uses sparse matrix multiplication and vector-matrix multiplication to perform perturbation term addition and row-column permutation on the plaintext matrix, thereby realizing the secret state calculation of sensitive data without leaking privacy information.

[0005] However, for the privacy-preserving computing process of hyperspectral remote sensing image data, in order to improve the efficiency of remote sensing analysis of user computing devices and reduce the additional overhead caused by privacy-preserving operations, it is necessary to further improve the privacy-preserving computing method and optimize the encryption, decryption and verification operations on the user side. Summary of the invention

[0006] In view of this, the present invention provides a privacy protection calculation method and system for hyperspectral remote sensing image data, which can improve the encryption and decryption efficiency of hyperspectral remote sensing images.

[0007] In order to achieve the above object, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention discloses a privacy protection computing method for hyperspectral remote sensing image data, wherein a user computing device, a key management center and a cloud server jointly participate in the computing process, including the following steps:

[0009] The key management center generates an index set as a key and sends it to the user computing device through a secure channel;

[0010] The user computing device uses the key sent by the key management center to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix according to the different privacy protection computing schemes that need to be executed, and sends the encrypted data to the cloud server;

[0011] The cloud server performs corresponding privacy-preserving calculations on the encrypted data according to the different privacy-preserving calculation schemes that need to be executed, and returns the confidential calculation results to the user's computing device;

[0012] The user's computing device verifies and decrypts the confidential computing results in a corresponding manner according to the different privacy-preserving computing schemes that need to be executed to obtain the final computing results.

[0013] Furthermore, the key management center randomly generates an index set , , , as the key;

[0014] When the user computing device needs to perform matrix multiplication privacy protection calculation, there are two hyperspectral remote sensing image matrices that need to be calculated. and , using the index set Pair Matrix Each element in is encrypted separately to obtain , and then use the index set right Each element of is encrypted separately, and we get ; Using index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get ;

[0015] When the user computing device needs to perform matrix pseudo-inverse privacy protection calculation, there is a hyperspectral remote sensing image matrix that needs to be calculated. , using the index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get .

[0016] Furthermore, the index set , and The generation process is the same as that of an index set of length n. The generation process includes:

[0017] Choose a random permutation function ;

[0018] Creating a permutation index ,in ;

[0019] Creating an Inverse Permutation Index ,in ;

[0020] Creating a Value Index , all its elements are initially set to 0;

[0021] Generates a loop where arrive common Wheel: Setting security parameters , in the interval Uniformly select random integers within and ,calculate ;calculate , ;

[0022] Generate key index set .

[0023] Furthermore, using the index set Pair Matrix Each element in is encrypted separately to obtain , expressed as:

[0024] ;

[0025] in, , ; Represents the row encryption and decryption function; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0026] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0027] ;

[0028] in, , ; represents the inverse column encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0029] Using Index Sets Pair Matrix Each element of is encrypted separately, and we get , expressed as:

[0030] ;

[0031] in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column;

[0032] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0033] ;

[0034] in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. OK Elements of a column.

[0035] Furthermore, the cloud server performs corresponding privacy-preserving calculations on the encrypted data according to different privacy-preserving calculation schemes to be executed, including:

[0036] When performing matrix multiplication privacy-preserving computations, the cloud server receives the encrypted matrix , , perform matrix multiplication calculation and get the calculation result , ;

[0037] When performing matrix pseudo-inverse privacy-preserving computation, the cloud server receives the encrypted matrix , perform matrix pseudo-inverse calculation, if , then the matrix The right inverse matrix of exists, and the cloud server calculates ;

[0038] if , then the matrix The left inverse matrix exists, and the cloud server calculates .

[0039] Furthermore, when performing privacy-preserving matrix multiplication calculations, the user computing device verifies the secret state calculation results based on the sampling detection idea. The verification process includes:

[0040] a) Generate verification rounds ;

[0041] b) Initialization verification results ;

[0042] c) Perform a cycle from arrive :

[0043] For each loop, two integers are randomly selected and , generates an integer pair ;from Extract the encrypted elements ;

[0044] Calculate verification elements ;

[0045] from No. Extract encrypted elements from the row ,from No. Extract encrypted elements from a column ;

[0046] Calculate verification elements , The range is variables, Representation Matrix The number of columns and matrix the number of rows, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0047] if ,make , and exit the loop; otherwise, continue the loop;

[0048] d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

[0049] Furthermore, when performing matrix pseudo-inverse privacy-preserving calculations, the user computing device verifies the confidential calculation results based on the sampling detection idea. The verification includes:

[0050] a) Generate verification rounds ;

[0051] b) Initialization verification results ;

[0052] c) Perform a cycle from arrive :

[0053] For each loop, two integers are randomly selected and , generates an integer pair ;

[0054] if , and perform a cycle from arrive :

[0055] from No. Row and Extract encrypted elements from each row and ,calculate , The range is variables, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0056] from No. Extract encrypted elements from the row ,calculate , Representation Matrix No. Line The elements of the column, Representation vector No. elements;

[0057] if , and perform a cycle from arrive :

[0058] from No. Column and Extract encrypted elements from columns and ,calculate , Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0059] from No. Extract encrypted elements from a column ,calculate , Representation Matrix No. Line Elements of a column;

[0060] Calculate verification elements ;

[0061] if ,make , and exit the loop; otherwise, continue the loop;

[0062] d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

[0063] Furthermore, when performing matrix multiplication privacy-preserving calculations, the process of decrypting the secret calculation results by the user computing device includes:

[0064] Using Index Sets Decryption For each element in , the decryption process is expressed as:

[0065] ;

[0066] in, , ; represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0067] Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as:

[0068] ;

[0069] in, represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements.

[0070] Furthermore, when performing matrix pseudo-inverse privacy-preserving calculations, the process of decrypting the secret state calculation results by the user computing device includes:

[0071] Using Index Sets Decryption For each element in , the decryption process is expressed as:

[0072] ;

[0073] Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as:

[0074] .

[0075] In a second aspect, the present invention discloses a privacy protection computing system for hyperspectral remote sensing image data, including: a user computing device, a key management center and a cloud server, which uses the method described above to perform encryption and decryption calculations on a hyperspectral remote sensing image matrix;

[0076] The key management center is used to generate an index set as a key and send it to the user computing device through a secure channel;

[0077] The user computing device is used to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix using the key sent by the key management center according to different privacy protection computing schemes that need to be executed, and send the encrypted data to the cloud server;

[0078] The cloud server is used to perform corresponding privacy-preserving calculations on the encrypted data according to different privacy-preserving calculation schemes that need to be executed, and return the confidential calculation results to the user's computing device;

[0079] The user computing device is used to verify and decrypt the confidential computing results in a corresponding manner according to the different privacy protection computing schemes that need to be executed to obtain the final computing results.

[0080] It can be seen from the above technical solutions that, compared with the prior art, the present invention has the following beneficial effects:

[0081] 1. The present invention provides a privacy-preserving computing solution for matrix multiplication and pseudo-inverse operations of hyperspectral remote sensing images. Users perform plaintext data encryption and decryption operations locally, and perform privacy-preserving computing of secret data on the cloud server, which reduces the burden of key storage and realizes efficient processing of hyperspectral remote sensing image data.

[0082] 2. The present invention uses the index set as the key to encrypt the hyperspectral remote sensing image data, and completes blind operations such as addition of disturbance terms and position replacement element by element, thereby reducing the key storage cost of the user's computing device and improving the efficiency of encryption and decryption of large-scale matrices.

[0083] 3. When verifying the privacy protection results, the present invention introduces efficient vector-matrix multiplication to complete the verification process based on the idea of ​​sampling detection, and uses ciphertext data to detect the correctness of the returned results, thereby ensuring the confidentiality of the plaintext data and the integrity and availability of the plaintext results, and speeding up the verification of the correctness of the results. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0085] Figure 1 A flowchart of the privacy protection calculation method for hyperspectral remote sensing image data provided by the present invention;

[0086] Figure 2 The present invention provides a flowchart of the method for privacy protection calculation of hyperspectral remote sensing image data when performing matrix pseudo-inverse privacy protection calculation. DETAILED DESCRIPTION

[0087] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0088] like Figure 1 As shown, the embodiment of the present invention discloses a privacy protection computing method for hyperspectral remote sensing image data, in which a user computing device, a key management center and a cloud server jointly participate in the computing process, including the following steps:

[0089] S1. The key management center generates an index set as a key and sends it to the user computing device through a secure channel;

[0090] S2. The user computing device uses the key sent by the key management center to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix according to different privacy protection computing schemes that need to be executed, and sends the encrypted data to the cloud server;

[0091] S3. The cloud server performs corresponding privacy-preserving calculations on the encrypted data according to the different privacy-preserving calculation schemes that need to be executed, and returns the confidential calculation results to the user's computing device;

[0092] S4. The user computing device verifies and decrypts the secret computing result in a corresponding manner according to the different privacy protection computing schemes that need to be executed to obtain the final computing result.

[0093] The above steps are further explained below.

[0094] S1. The key management center randomly generates an index set , , , as the key; index set , and The generation process is the same as that of As an example, for an index set of length n The generation process includes:

[0095] Choose a random permutation function ;

[0096] Creating a permutation index ,in ;

[0097] Creating an Inverse Permutation Index ,in ;

[0098] Creating a Value Index , all its elements are initially set to 0;

[0099] Generates a loop where arrive common Wheel: Setting security parameters , in the interval Uniformly select random integers within and ,calculate ;calculate , ;

[0100] Generate key index set .

[0101] S2. The user computing device uses the key sent by the key management center to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix according to the privacy protection computing scheme that needs to be executed, and sends the encrypted data to the cloud server; the privacy protection computing scheme that needs to be executed is matrix multiplication privacy protection computing or matrix pseudo-inverse privacy protection computing.

[0102] 1) When the user computing device needs to perform matrix multiplication privacy protection calculation, there are two hyperspectral remote sensing image matrices that need to be calculated. and , represents the set of real numbers, express The number of rows in the matrix, express The number of columns in the matrix is The number of rows in the matrix, express The number of columns in the matrix; use the index set Pair Matrix Each element in is encrypted separately to obtain , and then use the index set right Each element of is encrypted separately, and we get ; Using index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get ; Specifically include:

[0103] Using Index Sets Pair Matrix Each element in is encrypted separately to obtain , expressed as:

[0104] ;

[0105] in, , ; Represents the row encryption and decryption function; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0106] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0107] ;

[0108] in, , ; represents the inverse column encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0109] Using Index Sets Pair Matrix Each element of is encrypted separately, and we get , expressed as:

[0110] ;

[0111] in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column;

[0112] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0113] ;

[0114] in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. OK Elements of a column.

[0115] 2) When the user computing device needs to perform matrix pseudo-inverse privacy protection calculation, there is a hyperspectral remote sensing image matrix that needs to be calculated , using the index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get , specifically including:

[0116] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0117] ;

[0118] Using Index Sets right Each element of is encrypted separately, and we get , expressed as:

[0119] .

[0120] S3. The cloud server performs corresponding privacy-preserving calculations on the encrypted data according to the different privacy-preserving calculation schemes that need to be executed.

[0121] 1) When performing matrix multiplication privacy-preserving computation, the cloud server receives the encrypted matrix , , perform matrix multiplication calculation and get the calculation result , ;

[0122] 2) When performing matrix pseudo-inverse privacy-preserving computation, the cloud server receives the encrypted matrix , perform matrix pseudo-inverse calculation, if , then the matrix The right inverse matrix of exists, and the cloud server calculates ;

[0123] if , then the matrix The left inverse matrix exists, and the cloud server calculates .

[0124] S4. The user computing device verifies and decrypts the secret computing result in a corresponding manner according to the different privacy protection computing schemes that need to be executed to obtain the final computing result.

[0125] S41. The verification process includes:

[0126] A. When performing matrix multiplication privacy-preserving computation, the user’s computing device performs Verification algorithm, based on sampling detection idea to verify the encrypted calculation results, the user computing device calculates the encryption matrix and The user's computing device will check some of the elements in the calculation and compare the results of these calculations with the results returned by the cloud server. If all the selected elements pass the verification, the user's computing device will accept the returned results. The specific verification process includes:

[0127] a) Generate verification rounds ;

[0128] b) Initialization verification results ;

[0129] c) Perform a cycle from arrive :

[0130] For each loop, two integers are randomly selected and , generates an integer pair ;from Extract the encrypted elements ;

[0131] Calculate verification elements ;

[0132] from No. Extract encrypted elements from the row ,from No. Extract encrypted elements from a column ;

[0133] Calculate verification elements , The range is variables, Representation Matrix The number of columns and matrix the number of rows, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0134] if ,make , and exit the loop; otherwise, continue the loop;

[0135] d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

[0136] B. When performing matrix pseudo-inverse privacy-preserving computation, the user computing device executes the designed Verification algorithm, based on sampling detection idea to verify the encrypted calculation results, calculate the encryption matrix The user's computing device accepts the returned results if all selected elements pass the verification. The specific verification process includes:

[0137] a) Generate verification rounds ;

[0138] b) Initialization verification results ;

[0139] c) Perform a cycle from arrive :

[0140] For each loop, two integers are randomly selected and , generates an integer pair ;

[0141] if , and perform a cycle from arrive :

[0142] from No. Row and Extract encrypted elements from each row and ,calculate , The range is variables, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0143] from No. Extract encrypted elements from the row ,calculate , Representation Matrix No. Line The elements of the column, Representation vector No. elements;

[0144] if , and perform a cycle from arrive :

[0145] from No. Column and Extract encrypted elements from columns and ,calculate , Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column;

[0146] from No. Extract encrypted elements from a column ,calculate , Representation Matrix No. Line Elements of a column;

[0147] Calculate verification elements ;

[0148] if ,make , and exit the loop; otherwise, continue the loop;

[0149] d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

[0150] S42. The user computing device decrypts the secret computing result in a corresponding manner according to the different privacy protection computing schemes that need to be executed.

[0151] A. When performing privacy-preserving matrix multiplication calculations, the process of decrypting the secret calculation results by the user computing device includes:

[0152] Using Index Sets Decryption For each element in , the decryption process is expressed as:

[0153] ;

[0154] in, , ; represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements;

[0155] Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as:

[0156] ;

[0157] in, represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements.

[0158] Since S is eliminated during the privacy protection calculation process, the ciphertext result matrix is ​​protected by keys M and N, so S is not required for decryption.

[0159] B. When performing matrix pseudo-inverse privacy-preserving calculations, the process of decrypting the secret calculation results by the user computing device includes:

[0160] Using Index Sets Decryption For each element in , the decryption process is expressed as:

[0161] ;

[0162] Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as:

[0163] .

[0164] In other embodiments, the present invention further provides a privacy protection computing system for hyperspectral remote sensing image data, including: a user computing device, a key management center, and a cloud server, which uses the method described above to perform encryption and decryption calculations on a hyperspectral remote sensing image matrix;

[0165] The key management center is used to generate an index set as a key and send it to the user computing device through a secure channel;

[0166] The user computing device is used to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix using the key sent by the key management center according to different privacy protection computing schemes that need to be executed, and send the encrypted data to the cloud server;

[0167] The cloud server is used to perform corresponding privacy-preserving calculations on the encrypted data according to different privacy-preserving calculation schemes that need to be executed, and return the calculation results to the user's computing device;

[0168] The user computing device is used to verify and decrypt the calculation results in a corresponding manner according to the different privacy protection computing schemes that need to be executed to obtain the final calculation results.

[0169] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0170] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A privacy protection calculation method for hyperspectral remote sensing image data, characterized in that: The computing process is jointly participated by the user computing device, the key management center and the cloud server, including the following steps: The key management center generates an index set as a key and sends it to the user computing device D through a secure channel; The user computing device uses the key sent by the key management center to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix according to the different privacy protection computing schemes that need to be executed, and sends the encrypted data to the cloud server; The cloud server performs corresponding privacy-preserving calculations on the encrypted data according to the different privacy-preserving calculation schemes that need to be executed, and returns the confidential calculation results to the user's computing device; The user's computing device verifies and decrypts the confidential computing results in a corresponding manner according to the different privacy-preserving computing schemes that need to be executed to obtain the final computing results.

2. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 1, characterized in that: The key management center randomly generates an index set , , , as the key; When the user computing device needs to perform matrix multiplication privacy protection calculation, there are two hyperspectral remote sensing image matrices that need to be calculated. and , using index set Pair Matrix Each element in is encrypted separately to obtain , and then use the index set right Each element of is encrypted separately, and we get ; Using index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get ; When the user computing device needs to perform matrix pseudo-inverse privacy protection calculation, there is a hyperspectral remote sensing image matrix that needs to be calculated. , using index set Pair Matrix Each element of is encrypted separately, and we get , and then use the index set right Each element of is encrypted separately, and we get .

3. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 2 is characterized in that: Index Set , and The generation process is the same as that of an index set of length n. The generation process includes: Choose a random permutation function ; Creating a permutation index ,in ; Creating an Inverse Permutation Index ,in ; Creating a Value Index , all its elements are initially set to 0; Generates a loop where arrive common Wheel: Setting security parameters , in the interval Uniformly select random integers within and ,calculate ;calculate , ; Generate key index set .

4. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 2, characterized in that: Using Index Sets Pair Matrix Each element in is encrypted separately to obtain , expressed as: ； in, , ; Represents the row encryption and decryption function; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Using Index Sets right Each element of is encrypted separately, and we get , expressed as: ； in, , ; represents the inverse column encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Using Index Sets Pair Matrix Each element of is encrypted separately, and we get , expressed as: ； in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Using Index Sets right Each element of is encrypted separately, and we get , expressed as: ； in, , ; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Representation Matrix No. OK Elements of a column.

5. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 2, characterized in that: The cloud server performs corresponding privacy-preserving calculations on the encrypted data according to the different privacy-preserving calculation schemes that need to be executed, including: When performing matrix multiplication privacy-preserving computations, the cloud server receives the encrypted matrix , , perform matrix multiplication calculation and get the calculation result , ; When performing matrix pseudo-inverse privacy-preserving computation, the cloud server receives the encrypted matrix , perform matrix pseudo-inverse calculation, if , then the matrix The right inverse matrix of exists, and the cloud server calculates ; if , then the matrix The left inverse matrix exists, and the cloud server calculates .

6. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 5, characterized in that: When performing privacy-preserving matrix multiplication calculations, the user computing device verifies the secret state calculation results based on the sampling detection idea. The verification process includes: a) Generate verification rounds ; b) Initialization verification results ; c) Perform a cycle from arrive : For each loop, two integers are randomly selected and , generates an integer pair ;from Extract encrypted elements from ; Calculate verification elements ; from No. Extract encrypted elements from the row ,from No. Extract encrypted elements from a column ; Calculate verification elements , The range is variables, Representation Matrix The number of columns and matrix the number of rows, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column; if ,make , and exit the loop; otherwise, continue the loop; d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

7. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 5, characterized in that: When performing matrix pseudo-inverse privacy-preserving calculations, the user computing device verifies the secret state calculation results based on the sampling detection idea. The verification process includes: a) Generate verification rounds ; b) Initialization verification results ; c) Perform a cycle from arrive : For each loop, two integers are randomly selected and , generates an integer pair ; if , and perform a cycle from arrive : from No. Row and Extract encrypted elements from each row and ,calculate , The range is variables, Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column; from No. Extract encrypted elements from the row ,calculate , Representation Matrix No. Line The elements of the column, Representation vector No. elements; if , and perform a cycle from arrive : from No. Column and Extract encrypted elements from columns and ,calculate , Representation Matrix No. Line The elements of the column, Representation Matrix No. Line Elements of a column; from No. Extract encrypted elements from a column ,calculate , Representation Matrix No. Line Elements of a column; Calculate verification elements ; if ,make , and exit the loop; otherwise, continue the loop; d) Get verification results ,like , then the verification is passed and the user computing device accepts Otherwise, reject .

8. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 5, characterized in that: When performing matrix multiplication privacy-preserving calculations, the process of decrypting the secret calculation results by the user computing device includes: Using Index Sets Decryption For each element in , the decryption process is expressed as: ； in, , ; represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as: ； in, represents the reverse encryption and decryption function; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Represents an index No. elements; Represents an index No. elements; Representation Matrix No. Line Elements of a column; Representation Matrix No. Line Elements of a column; Represents an index No. elements.

9. The privacy protection calculation method for hyperspectral remote sensing image data according to claim 5, characterized in that: When performing matrix pseudo-inverse privacy-preserving calculations, the process of decrypting the secret calculation results by the user computing device includes: Using Index Sets Decryption For each element in , the decryption process is expressed as: ； Using Index Sets Decryption Each element in gets the final calculation result , the decryption process is expressed as: 。 10. A privacy protection computing system for hyperspectral remote sensing image data, characterized in that: include: The user computing device, the key management center and the cloud server perform encryption and decryption calculations on the hyperspectral remote sensing image matrix using the method described in any one of claims 1 to 9; The key management center is used to generate an index set as a key and send it to the user computing device through a secure channel; The user computing device is used to perform corresponding encryption calculations on the hyperspectral remote sensing image matrix using the key sent by the key management center according to different privacy protection computing schemes that need to be executed, and send the encrypted data to the cloud server; The cloud server is used to perform corresponding privacy-preserving calculations on the encrypted data according to different privacy-preserving calculation schemes that need to be executed, and return the confidential calculation results to the user's computing device; The user computing device is used to verify and decrypt the confidential computing results in a corresponding manner according to the different privacy protection computing schemes that need to be executed to obtain the final computing results.

Images