Method and apparatus for signaling data protection and analysis, electronic device, and storage medium

Abstract

The present application relates to a kind of signaling data protection and analysis method, device, electronic equipment and storage medium.Signal data protection and analysis method includes the steps of: data collection;Data preprocessing;Metadata generation;Mixing homomorphic encryption, Paillier encryption is used by default, if there is re-encryption requirement, then according to re-encryption requirement notification switch to EIGamal encryption scheme;Data transmission;Re-encryption requirement notification, third party institution carries out statistical analysis on the data of ciphertext, when doing addition and subtraction operation, directly use the ciphertext data provided by data provider, when third party institution needs to do multiplication or division on ciphertext, then through the re-encryption requirement notification service of calling data provider, operation type and metadata are transmitted back to data provider, and data provider restores signaling plaintext after metadata query, and then is re-encrypted by EIGamal, and is transmitted to third party institution by data transmission module, to realize the self-adaptation of homomorphic encryption.

Description

Technical Field

[0001] This invention relates to the field of communications, and more specifically, to a method, apparatus, electronic device, and storage medium for signaling data protection and analysis. Background Technology

[0002] With the rapid development of telecommunications networks and mobile internet, signaling data has become a crucial asset for telecom operators, government agencies, and third-party service providers. Signaling data not only contains basic information about the communicating parties but also a wealth of sensitive information, such as call initiation time, ringing time, and call duration. It has wide applications in network optimization, user behavior analysis, and fraud detection. However, with the widespread adoption of big data and cloud computing technologies, serious data security and privacy protection issues arise when this data needs to be shared among multiple parties or submitted to third-party organizations for analysis.

[0003] Existing solutions also have their limitations. Traditional encryption methods: Current signaling data protection schemes mainly rely on traditional encryption technologies such as AES or RSA. While these methods effectively protect data privacy, no effective data analysis or processing can be performed before the data is decrypted. This is impractical in scenarios requiring real-time analysis or large-scale data processing. Homomorphic encryption: Homomorphic encryption is divided into fully homomorphic encryption (FHE) and partially homomorphic encryption (PHE). Fully homomorphic encryption can support any arithmetic operation simultaneously, but its high computational complexity makes it difficult to engineer and it remains in the research stage. Partially homomorphic encryption is simple and efficient, but it cannot support both addition and multiplication operations simultaneously, which greatly limits data analysis capabilities. Differential privacy: Differential privacy is another commonly used data protection method that protects individual data by adding random noise. However, differential privacy uses plaintext data, and this method reduces data accuracy and may expose private information under multiple queries. Secure multi-party computation: This is a method that allows multiple parties to perform computations without revealing their respective data. However, this method has high computational complexity and is not suitable for large-scale data processing.

[0004] Therefore, how to ensure that user privacy is not leaked, and how to achieve data privacy and security while enabling limited data processing and analysis in an encrypted state, and to perform efficient data computation, has become an urgent problem to be solved. Summary of the Invention

[0005] The technical problem this invention aims to solve is how to ensure that user privacy is not leaked, and how to perform limited data processing and analysis in an encrypted state while guaranteeing signaling data privacy and data security, and to perform efficient data computation.

[0006] To address the aforementioned technical problems, according to one aspect of the present invention, a method for signaling data protection and analysis is provided, comprising the following steps:

[0007] Data collection involves obtaining raw signaling data from data sources, inputting raw signaling data, collecting data through methods including socket API calls, database queries, or other data interfaces, and outputting structured signaling data.

[0008] Data preprocessing involves cleaning and formatting the structured signaling data, using data cleaning algorithms and data transformation methods to de-identify the calling and called numbers, and generating the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC (Hash-based Message Authentication Code), outputting the original and derived features of the signaling.

[0009] Metadata generation involves generating metadata for each preprocessed signaling data. UUIDs are used to encode metadata for each signaling message and save it to a database or distributed storage system. One metadata record is generated for each signaling message, and a globally unique, meaningless metadata code is output. The metadata contains sensitive information and is globally unique.

[0010] Hybrid homomorphic encryption uses a hybrid homomorphic encryption scheme of Paillier and EIGamal to encrypt or decrypt signaling feature values. Paillier encryption is used by default. If there is a need for re-encryption, the system will switch to the EIGamal encryption scheme according to the re-encryption requirement.

[0011] Data transmission is performed via the socket HTTPS API interface, transmitting encrypted data and metadata to third-party organizations in the form of metadata plus signaling data ciphertext.

[0012] The re-encryption request notification allows third-party organizations to perform statistical analysis on encrypted data. When performing addition and subtraction operations on the encrypted data, they directly use the encrypted data provided by the data provider, as the data provider's default encryption method supports Paillier for addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption request notification service, sending the operation type and metadata back to the data provider. The data provider then reconstructs the plaintext signaling after querying the metadata, re-encrypts it using EIGamal, and transmits it to the third-party organization through the data transmission module, thus achieving adaptive homomorphic encryption.

[0013] According to an embodiment of the present invention, in step S4, a hybrid homomorphic encryption scheme of Paillier and EIGamal can be used to encrypt or decrypt the signaling feature value, with the input being encryption type, metadata, and plaintext.

[0014] Specifically, when the encryption type encrypts the preprocessed metadata, Paillier encryption is used, and the output is the Paillier-encrypted ciphertext; when the metadata requiring re-encryption is encrypted, EIGamal encryption is used, and the output is the EIGamal-encrypted ciphertext; the Paillier and EIGamal encryption algorithms are implemented in Java and Python respectively.

[0015] The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

[0016] According to embodiments of the present invention, Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext. Paillier encryption may include the following steps:

[0017] S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers;

[0018] S412, Calculate the modulus n and γ

[0019] n = p × q

[0020] γ = lcm(p-1, q-1)

[0021] Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1;

[0022] S413. Choose an integer g such that gcd(L(g γ mod n 2 ), n)=1,

[0023] Where L(x) = (x-1) / n, and gcd is the greatest common divisor;

[0024] S414. Generate a key, which includes a public key and a private key.

[0025] The public key is (n, g), and the private key is (γ, μ).

[0026] Where, μ=L(g γ mod n 2 ) -1 mod n;

[0027] S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy...

[0028] gcd(r, n) = 1,

[0029] Then through c=g M ×r n mod n 2 Calculate the ciphertext;

[0030] S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal.

[0031] When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2;

[0032] In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m2 ×r n mod n 2 ,then

[0033] c m1-m2 =c m1 ×c m2 mod n 2 , where c m1-m2 It's an encryption of m1-m2.

[0034] The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

[0035] According to embodiments of the present invention, EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext. EIGamal encryption may include the following steps:

[0036] S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p;

[0037] S422, Generate key.

[0038] Private key: randomly select an integer x, 1 <x<p-1;

[0039] Public key: Calculate y = g x mod p

[0040] S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1;

[0041] S424, Calculate c1 and c2

[0042] Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2);

[0043] S425. Perform multiplication or division operations.

[0044] The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows:

[0045] C13 = C11 × C12 mod p

[0046] C23 = C21 × C22 mod p

[0047] The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2 ), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps:

[0048]

[0049] Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext. The calculation formula is:

[0050]

[0051] in, for Encryption;

[0052] Decrypting the encrypted content involves calculating s:

[0053]

[0054] Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

[0055] According to a second aspect of the present invention, an apparatus for signaling data protection and analysis is provided, comprising:

[0056] The data collection module is used to obtain raw signaling data from the data source, input raw signaling data, collect data through socket API calls, database queries or other data interfaces, and output structured signaling data.

[0057] The data preprocessing module is used to clean and format the structured signaling data. It uses data cleaning algorithms and data transformation methods to de-identify the calling and called numbers and generate the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC (Hash-based Message Authentication Code), and the original and derived features of the signaling are output.

[0058] The metadata generation module is used to generate metadata for each preprocessed signaling data. It uses UUID to encode the metadata for each signaling and saves it to a database or distributed storage system. It generates one metadata for each signaling and outputs a globally unique meaningless metadata code. The metadata contains sensitive information and is globally unique.

[0059] The hybrid homomorphic encryption module is used to encrypt or decrypt signaling feature values ​​using a hybrid homomorphic encryption scheme of Paillier and EIGamal. Paillier encryption is used by default; if there is a need for re-encryption, the module will switch to the EIGamal encryption scheme according to the re-encryption requirement.

[0060] The data transmission module is used to transmit encrypted data and metadata to third-party organizations via the socket HTTPS API interface, in the form of metadata plus signaling data ciphertext.

[0061] The re-encryption request notification module is used by third-party organizations to perform statistical analysis on encrypted data. When the third-party organization performs addition and subtraction operations on the encrypted data, it directly uses the encrypted data provided by the data provider, because the data provider's default data encryption method supports Paillier, which supports addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption request notification service, sending the operation type and metadata back to the data provider. After the data provider restores the plaintext signaling by querying the metadata, it re-encrypts it with EIGamal and transmits it to the third-party organization through the data transmission module, thus achieving adaptive homomorphic encryption.

[0062] According to embodiments of the present invention, the hybrid homomorphic encryption module can use the Paillier and EIGamal hybrid homomorphic encryption scheme to encrypt or decrypt signaling feature values, with the input being encryption type, metadata, and plaintext.

[0063] Specifically, when the encryption type encrypts the preprocessed metadata, Paillier encryption is used, and the output is the Paillier-encrypted ciphertext; when the metadata requiring re-encryption is encrypted, EIGamal encryption is used, and the output is the EIGamal-encrypted ciphertext; the Paillier and EIGamal encryption algorithms are implemented in Java and Python respectively.

[0064] The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

[0065] According to embodiments of the present invention, Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext. Paillier encryption may include the following steps:

[0066] S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers;

[0067] S412, Calculate the modulus n and γ

[0068] n = p × q

[0069] γ = lcm(p-1, q-1)

[0070] Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1;

[0071] S413. Choose an integer g such that gcd(L(g γ mod n 2 ), n)=1,

[0072] Where L(x) = (x-1) / n, and gcd is the greatest common divisor;

[0073] S414. Generate a key, which includes a public key and a private key.

[0074] The public key is (n, g), and the private key is (γ, μ).

[0075] Where, μ=L(g γ mod n 2 ) -1 mod n;

[0076] S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy...

[0077] gcd(r, n) = 1,

[0078] Then through c=g M ×r n mod n 2 Calculate the ciphertext;

[0079] S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal.

[0080] When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2;

[0081] In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m 2×r n mod n 2 ,then

[0082] c m1-m2 =c m1 ×c m2 mod n 2, where c m1-m2 It's an encryption of m1-m2.

[0083] The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

[0084] According to embodiments of the present invention, EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext. EIGamal encryption may include the following steps:

[0085] S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p;

[0086] S422, Generate key.

[0087] Private key: randomly select an integer x, 1 <x<p-1;

[0088] Public key: used to compute y = g x mod p

[0089] S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1;

[0090] S424, Calculate c1 and c2

[0091] Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2);

[0092] S425. Perform multiplication or division operations.

[0093] The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows:

[0094] C13 = C11 × C12 mod p

[0095] C23 = C21 × C22 mod p

[0096] The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2 ), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps:

[0097]

[0098] Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext. The calculation formula is:

[0099]

[0100] in, for Encryption;

[0101] Decrypting the encrypted content involves calculating s:

[0102]

[0103] Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

[0104] According to a third aspect of the present invention, an electronic device is provided, comprising: a memory, a processor, and wherein the memory stores a signaling data protection and analysis program executable on the processor, wherein when the signaling data protection and analysis program is executed by the processor, it implements the steps of the signaling data protection and analysis method described above.

[0105] According to a fourth aspect of the present invention, a computer storage medium is provided, wherein a signaling data protection and analysis program is stored on the computer storage medium, and when the signaling data protection and analysis program is executed by a processor, it implements the steps of the signaling data protection and analysis method described above.

[0106] Compared with the prior art, the technical solution provided by the embodiments of the present invention can achieve at least the following beneficial effects:

[0107] The signaling data protection and analysis method provided by this invention is adaptive, enabling the encryption system to automatically switch as needed without employing complex, software-engineering-impractical fully homomorphic encryption. Through the adaptive homomorphic encryption technology of this invention, not only is efficient computation achieved without decryption, but the efficiency of homomorphic encryption is also significantly improved, thus demonstrating a clear advantage over existing technologies.

[0108] The signaling data protection and analysis method provided by this invention can achieve adaptability in homomorphic encryption algorithm selection. Through a re-encryption requirement notification mechanism, third-party organizations can notify data providers via API or other communication methods, indicating which type of encryption operation they need to perform. Then, the data provider can re-encrypt the data according to these requirements, and the third-party organization can complete relatively complex data analysis tasks in an environment that does not require plaintext.

[0109] The signaling data protection and analysis method provided by this invention uses hybrid homomorphic encryption to solve the problem of diverse computation types. It designs a Paillier+ElGamal hybrid homomorphic encryption algorithm suitable for communication signaling data, which enables the algorithm to support both addition and multiplication operations on the ciphertext at the same time. Furthermore, it can extend the addition and multiplication operations to include subtraction and division operations, thereby allowing third-party organizations to perform relatively complex data statistical analysis and machine learning model training without decryption.

[0110] The metadata-assisted homomorphic encryption and decryption strategy designed in this invention reduces the complexity of some homomorphic encryption calculations and avoids decryption operations by the data provider, thereby greatly reducing the complexity of system encryption and solving the limitation that some homomorphic encryption cannot simultaneously support addition and multiplication in the scenario of protecting signaling data.

[0111] The signaling data protection and analysis method provided by this invention implements a metadata-assisted homomorphic encryption and decryption strategy. It generates metadata for each signaling message, which does not contain sensitive information. The data provider establishes a one-to-one correspondence between metadata, plaintext, and encrypted data and stores this information within its system. Data transmitted to third-party organizations contains only metadata and ciphertext, allowing them to more easily identify which data can be batch-processed together. This enables them to complete multiple computational tasks at once, rather than one by one, thus improving computational efficiency. Furthermore, with metadata, the data provider's decryption operation is simplified to a query operation based on the metadata. When a third party requires a specific homomorphic encryption algorithm, it only needs to send the signaling metadata and encryption type back to the data provider. The data provider can then retrieve the plaintext based on the metadata, eliminating the decryption process and significantly improving the system's computational efficiency.

[0112] The metadata-assisted homomorphic encryption and decryption strategy designed in this invention improves the computational efficiency of data homomorphic encryption and decryption as well as the data transmission efficiency. It allows third-party organizations to send back batches of metadata for batch homomorphic encryption calculations, significantly improving the efficiency of data encryption processing and data transmission.

[0113] The signaling data protection and analysis method provided by this invention is adaptable and scalable. Due to its modular design, the solution of this invention can easily adapt to different types of data and application scenarios, and is also easy to combine with other data protection or analysis methods.

[0114] This invention provides sensitive data protection for signaling data, while ensuring that the encrypted data retains its analyzability, including the ability to perform statistical analyses. This invention is not limited to signaling data encryption; it can also be used for statistical analysis of user data containing integer features or for common machine learning tasks.

[0115] This invention effectively addresses several limitations of existing solutions, particularly in big data and machine learning applications. It employs core technologies such as adaptive homomorphic encryption based on a re-encryption requirement notification mechanism, hybrid homomorphic encryption, and metadata-assisted homomorphic encryption / decryption strategies, providing an innovative solution to this problem with significant theoretical and practical value. It is expected to find widespread application in future communication networks. Attached Figure Description

[0116] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments will be briefly described below. Obviously, the drawings described below only relate to some embodiments of the present invention and are not intended to limit the present invention.

[0117] Figure 1 This is a schematic diagram illustrating the adaptive homomorphic encryption process according to an embodiment of the present invention.

[0118] Figure 2 This is a schematic diagram illustrating the metadata query process according to an embodiment of the present invention. Detailed Implementation

[0119] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the described embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0120] Unless otherwise defined, the technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains. The terms “first,” “second,” and similar terms used in the specification and claims of this patent application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Similarly, the terms “an” or “a” and similar terms do not indicate a limitation of quantity, but rather indicate the presence of at least one.

[0121] Figure 1 This is a schematic diagram illustrating the adaptive homomorphic encryption process according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the metadata query process according to an embodiment of the present invention.

[0122] like Figure 1 and Figure 2 As shown, the method for signaling data protection and analysis includes the following steps:

[0123] Data collection involves obtaining raw signaling data from data sources, inputting raw signaling data, collecting data through methods including socket API calls, database queries, or other data interfaces, and outputting structured signaling data.

[0124] Data preprocessing involves cleaning and formatting the structured signaling data, using data cleaning algorithms and data transformation methods to de-identify the calling and called numbers, and generating the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC (Hash-based Message Authentication Code), outputting the original and derived features of the signaling.

[0125] Metadata generation involves generating metadata for each preprocessed signaling data. UUIDs are used to encode metadata for each signaling message and save it to a database or distributed storage system. One metadata record is generated for each signaling message, and globally unique, meaningless metadata codes are output. Metadata contains sensitive information and is globally unique.

[0126] Hybrid homomorphic encryption uses a hybrid homomorphic encryption scheme of Paillier and EIGamal to encrypt or decrypt signaling feature values. Paillier encryption is used by default. If there is a need for re-encryption, the system will switch to the EIGamal encryption scheme according to the re-encryption requirement.

[0127] Data transmission is performed via the socket HTTPS API interface, transmitting encrypted data and metadata to third-party organizations in the form of metadata plus signaling data ciphertext.

[0128] The re-encryption request notification allows third-party organizations to perform statistical analysis on encrypted data. When performing addition and subtraction operations on the encrypted data, they directly use the encrypted data provided by the data provider, as the data provider's default encryption method supports Paillier for addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption request notification service, sending the operation type and metadata back to the data provider. The data provider then reconstructs the plaintext signaling after querying the metadata, re-encrypts it using EIGamal, and transmits it to the third-party organization through the data transmission module, thus achieving adaptive homomorphic encryption.

[0129] The signaling data protection and analysis method provided by this invention uses hybrid homomorphic encryption to solve the problem of diverse computation types. It designs a Paillier+ElGamal hybrid homomorphic encryption algorithm suitable for communication signaling data, which enables the algorithm to support both addition and multiplication operations on the ciphertext at the same time. Furthermore, it can extend the addition and multiplication operations to include subtraction and division operations, thereby allowing third-party organizations to perform relatively complex data statistical analysis and machine learning model training without decryption.

[0130] The metadata-assisted homomorphic encryption and decryption strategy designed in this invention improves the computational efficiency of data homomorphic encryption and decryption as well as the data transmission efficiency. It allows third-party organizations to send back batches of metadata for batch homomorphic encryption calculations, significantly improving the efficiency of data encryption processing and data transmission.

[0131] According to one or more embodiments of the present invention, in step S4, the signaling feature value is encrypted or decrypted using a Paillier / EIGamal hybrid homomorphic encryption scheme, with the input being encryption type, metadata, and plaintext.

[0132] For example, the encryption type is set to 1 when encrypting preprocessed metadata, and set to 2 when encrypting metadata that requires re-encryption. When the encryption type is 1, Paillier encryption is used, and the output is the ciphertext encrypted by Paillier. When the encryption type is 2, EIGamal encryption is used, and the output is the ciphertext encrypted by EIGamal. The Paillier and EIGamal encryption algorithms are implemented in Java and Python.

[0133] The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

[0134] According to one or more embodiments of the present invention, Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext. Paillier encryption includes the following steps:

[0135] S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers;

[0136] S412, Calculate the modulus n and γ

[0137] n = p × q

[0138] γ = lcm(p-1, q-1)

[0139] Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1;

[0140] S413. Choose an integer g such that gcd(L(g γ mod n 2 ), n)=1,

[0141] Where L(x) = (x-1) / n, and gcd is the greatest common divisor;

[0142] S414. Generate a key, which includes a public key and a private key.

[0143] The public key is (n, g), and the private key is (γ, μ).

[0144] Where, μ=L(g γ mod n 2 ) -1 mod n;

[0145] S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy...

[0146] gcd(r, n) = 1,

[0147] Then through c=g M ×r n mod n 2 Calculate the ciphertext;

[0148] S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal.

[0149] When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2;

[0150] In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m2 ×r n mod n 2 ,then

[0151] c m1-m2 =c m1 ×c m2 mod n 2 , where c m1-m2 It's an encryption of m1-m2.

[0152] The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

[0153] According to one or more embodiments of the present invention, EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext. EIGamal encryption includes the following steps:

[0154] S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p;

[0155] S422, Generate key.

[0156] Private key: randomly select an integer x, 1 <x<p-1;

[0157] Public key: used to compute y = g x mod p

[0158] S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1;

[0159] S424, Calculate c1 and c2

[0160] Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2);

[0161] S425. Perform multiplication or division operations.

[0162] The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows:

[0163] C13 = C11 × C12 mod p

[0164] C23 = C21 × C22 mod p

[0165] The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2 ), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps:

[0166]

[0167] Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext. The calculation formula is:

[0168]

[0169] in, for Encryption;

[0170] Decrypting the encrypted content involves calculating s:

[0171]

[0172] Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

[0173] This invention provides sensitive data protection for signaling data, while ensuring that the encrypted data retains its analyzability, including the ability to perform statistical analyses. This invention is not limited to signaling data encryption; it can also be used for statistical analysis of user data containing integer features or for common machine learning tasks.

[0174] According to a second aspect of the present invention, an apparatus for signaling data protection and analysis is provided, comprising: a data collection module, a data preprocessing module, a metadata generation module, a hybrid homomorphic encryption module, a data transmission module, and a re-encryption requirement notification module.

[0175] The data collection module is used to obtain raw signaling data from the data source, input raw signaling data, collect data through methods including socket API calls, database queries or other data interfaces, and output structured signaling data.

[0176] The data preprocessing module is used to clean and format the structured signaling data. It uses data cleaning algorithms and data transformation methods to de-identify the calling and called numbers and generate the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC (Hash-based Message Authentication Code), which outputs the original and derived features of the signaling.

[0177] The metadata generation module is used to generate metadata for each preprocessed signaling data. It uses UUID to encode the metadata for each signaling and saves it to a database or distributed storage system. It generates one metadata for each signaling and outputs a globally unique, meaningless metadata code. The metadata contains sensitive information and is globally unique.

[0178] The hybrid homomorphic encryption module is used to encrypt or decrypt signaling feature values ​​using a hybrid homomorphic encryption scheme of Paillier and EIGamal. Paillier encryption is used by default; if there is a need for re-encryption, the module will switch to the EIGamal encryption scheme according to the re-encryption requirement.

[0179] The data transmission module is used to transmit encrypted data and metadata to third-party organizations via the socket HTTPS API interface, in the form of metadata plus signaling data ciphertext.

[0180] The re-encryption requirement notification module is used by third-party organizations to perform statistical analysis on encrypted data. When the third-party organization performs addition and subtraction operations on the encrypted data, it directly uses the encrypted data provided by the data provider, because the default data encryption method of the data provider supports Paillier, which supports addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption requirement notification service, sends the operation type and metadata back to the data provider, and the data provider restores the signaling plaintext after querying the metadata, re-encrypts it with EIGamal, and then transmits it to the third-party organization through the data transmission module, thus realizing the adaptive homomorphic encryption.

[0181] The metadata-assisted homomorphic encryption and decryption strategy designed in this invention reduces the complexity of some homomorphic encryption calculations and avoids decryption operations by the data provider, thereby significantly reducing the complexity of system encryption. It also addresses the limitation that some homomorphic encryption methods cannot simultaneously support addition and multiplication in signaling data protection scenarios. The signaling data protection and analysis method provided by this invention enables adaptive homomorphic encryption algorithm selection. Through a re-encryption requirement notification mechanism, third-party organizations can notify data providers via API or other communication methods, indicating the type of encryption operation they need. The data provider can then re-encrypt the data according to these requirements, allowing third-party organizations to complete relatively complex data analysis tasks in an environment that does not require plaintext.

[0182] According to one or more embodiments of the present invention, the hybrid homomorphic encryption module uses the Paillier and EIGamal hybrid homomorphic encryption scheme to encrypt or decrypt signaling feature values, with the input being encryption type, metadata, and plaintext.

[0183] For example, the encryption type is set to 1 when encrypting preprocessed metadata, and set to 2 when encrypting metadata that requires re-encryption. When the encryption type is 1, Paillier encryption is used, and the output is the ciphertext encrypted by Paillier. When the encryption type is 2, EIGamal encryption is used, and the output is the ciphertext encrypted by EIGamal. The Paillier and EIGamal encryption algorithms are implemented in Java and Python.

[0184] The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

[0185] According to one or more embodiments of the present invention, Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext. Paillier encryption includes the following steps:

[0186] S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers;

[0187] S412, Calculate the modulus n and γ

[0188] n = p × q

[0189] γ = lcm(p-1, q-1)

[0190] Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1;

[0191] S413. Choose an integer g such that gcd(L(g γmod n 2 ), n)=1,

[0192] Where L(x) = (x-1) / n, and gcd is the greatest common divisor;

[0193] S414. Generate a key, which includes a public key and a private key.

[0194] The public key is (n, g), and the private key is (γ, μ).

[0195] Where, μ=L(g γ mod n 2 ) -1 mod n;

[0196] S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy...

[0197] gcd(r, n) = 1,

[0198] Then through c=g M ×r n mod n 2 Calculate the ciphertext;

[0199] S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal.

[0200] When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2;

[0201] In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m 2×r n mod n 2 ,then

[0202] c m1-m2=c m1 ×c m2 mod n 2 , where c m1-m2 It's an encryption of m1-m2.

[0203] The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

[0204] According to one or more embodiments of the present invention, EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext. EIGamal encryption includes the following steps:

[0205] S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p;

[0206] S422, Generate key.

[0207] Private key: randomly select an integer x, 1 <x<p-1;

[0208] Public key: used to compute y = g x mod p

[0209] S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1;

[0210] S424, Calculate c1 and c2

[0211] Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2);

[0212] S425. Perform multiplication or division operations.

[0213] The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows:

[0214] C13 = C11 × C12 mod p

[0215] C23=C21×C22 mod p

[0216] The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps:

[0217]

[0218] Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext. The calculation formula is:

[0219]

[0220] in, for Encryption;

[0221] Decrypting the encrypted content involves calculating s:

[0222]

[0223] Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

[0224] The signaling data protection and analysis method provided by this invention is adaptive, enabling the encryption system to automatically switch as needed without employing complex, software-engineering-impractical fully homomorphic encryption. Through the adaptive homomorphic encryption technology of this invention, not only is efficient computation achieved without decryption, but the efficiency of homomorphic encryption is also significantly improved, thus demonstrating a clear advantage over existing technologies.

[0225] The signaling data protection and analysis method provided by this invention is adaptable and scalable. Due to its modular design, the solution can easily adapt to different types of data and application scenarios, and is also easy to combine with other data protection or analysis methods. This invention effectively solves several limitations of existing solutions, especially in big data and machine learning application scenarios. This invention employs core technologies such as adaptive homomorphic encryption based on a re-encryption requirement notification mechanism, hybrid homomorphic encryption, and metadata-assisted homomorphic encryption / decryption strategies, providing an innovative solution to this problem with significant theoretical and practical value. It is expected to be widely used in future communication networks.

[0226] In use, the signaling data in the communication network is protected and analyzed using the method of this embodiment, as detailed below:

[0227] First, data collection is performed, collecting signaling data from different data sources. This invention uses the Netty framework to collect raw signaling from communication links such as provincial C-networks and core networks, and decodes the raw signaling in the communication links into CDR signaling data format with business meaning according to the protocols of various manufacturers.

[0228] Next, data preprocessing is performed to initially process the raw signaling data to facilitate subsequent homomorphic encryption operations. The specific steps are as follows:

[0229] (1) De-identification of calling and called numbers: Extract the calling and called numbers from the original signaling data and de-identify them using HMAC (Hash Authentication Code).

[0230] (2) Extracting numerical features from signaling: Extracting numerical features such as call initiation time, ringing time, call duration, and answer time from the original signaling data. The CDR signaling data structure is shown below:

[0231]

[0232]

[0233] (3) Data cleaning: Remove incomplete or incorrect records to ensure data quality.

[0234] After data cleaning, a complete CDR signaling data sample is roughly as follows (simulated data):

[0235]

[0236]

[0237] Next, metadata is generated for each piece of collected signaling data. This metadata is used to assist in the homomorphic encryption and decryption process, as well as subsequent data analysis.

[0238] Input: Raw signaling data, including but not limited to: call initiation time, ringing time, and call duration.

[0239] Output: An array of metadata, each element containing a unique identifier (using UUID) and other attributes for a single signaling data entry. Assume we have the following signaling data (note: calling and called parties are omitted, values ​​are in milliseconds):

[0240] Specific implementation methods for obtaining plaintext through metadata query:

[0241] (1) During the data transmission phase: the encrypted data and metadata array (the metadata is in plaintext) are securely transmitted to a third-party organization.

[0242] (2) Third-party analysis stage: The third-party organization performs necessary homomorphic operations. If it needs to perform unsupported operations (such as division), the third-party organization notifies the data provider through a re-encryption notification mechanism.

[0243] (3) Re-encryption notification stage: The third-party organization selects the UUIDs that need to be re-encrypted, and sends these UUIDs (which can be sent back in batches) and the new encryption algorithm type back to the data provider.

[0244] (4) Data provider query stage: The data provider receives the UUID and the new encryption algorithm type, and uses the metadata array to query the original signaling data corresponding to these UUIDs.

[0245] (5) Data provider re-encryption stage: The data provider uses a new encryption algorithm to re-encrypt the original signaling data.

[0246] (6) Third-party organization continues analysis: The third-party organization receives the re-encrypted data and continues to analyze it.

[0247] The metadata array is composed as follows:

[0248]

[0249] Furthermore, hybrid homomorphic encryption is implemented using two different homomorphic encryption schemes: Paillier and EIGamal. The choice of which encryption scheme to use can be dynamically selected based on user or system requirements. This module primarily includes two API methods: encrypt and decrypt.

[0250] Input / Output

[0251] Encryption method (encrypt)

[0252] Input: Encryption type parameter (1 or 2), metadata, plaintext.

[0253] Output: Ciphertext and metadata under the corresponding encryption scheme.

[0254] Decryption method (decrypt)

[0255] Input: Metadata.

[0256] Output: Find the corresponding plaintext by querying the metadata.

[0257] Main API methods

[0258] Encryption method (encrypt)

[0259] Parameters: encryptionType: encryption type (1: Paillier, 2: EIGamal), metadata: metadata, plaintext: plaintext data

[0260] Output: Encrypted ciphertext and metadata

[0261] Logic: If encryptionType is 1, use the Paillier encryption algorithm for encryption. If encryptionType is 2, use the EIGamal encryption algorithm for encryption.

[0262] Decryption method (decrypt)

[0263] Parameter: metadata: metadata

[0264] Output: Plaintext data

[0265] Logic: Retrieve plaintext data by querying metadata. No decryption using Paillier or EIGamal is required.

[0266] The encrypted signaling data looks like this (Note: The encrypted data is simulated data, not real encrypted data):

[0267] Finally, a re-encryption requirement notification is sent. Since the signaling data received by the third party is generated using Paillier encryption by default, it can only perform addition (or subtraction). When the third party needs to perform multiplication (or division), it only needs to send the metadata and encryption class type back to the data provider via the HTTPS interface. The data provider then calls the hybrid homomorphic encryption API interface of this system to perform multiplication or division using EIGamal encryption (note: it may also be Paillier addition or subtraction, because the same data may be repeatedly encrypted under different statistical requirements), and sends the encryption result and the data back to the third party.

[0268] (1) Initialization phase: Establish a secure communication channel between DPF and TPI, specifically:

[0269] Obtaining an SSL / TLS Certificate

[0270] DPF and TPI require SSL / TLS certificates to be obtained from a trusted CA.

[0271] Installation Certificate

[0272] Install the obtained certificates onto their respective servers.

[0273] Configure HTTPS

[0274] In the server's configuration file, enable HTTPS and specify the location of the certificate and private key.

[0275] Test connection

[0276] After enabling HTTPS, you can test the secure connection using a browser or other tools.

[0277] API Design

[0278] On this secure channel, DPF and TPI can design a set of RESTful APIs.

[0279] (2) Re-encryption notification:

[0280] When a third party needs to perform multiplication (or division), it needs to notify the data provider to re-encrypt the data. This notification information (which can be returned in batches via a secure channel established during the initialization phase) is transmitted to the data provider.

[0281] In this way, when the data provider receives the re-encryption notification request, it parses the calculation type in the message as division, retrieves the corresponding signaling plaintext based on the metadata in the message, calls the hybrid homomorphic encryption module to perform a new encryption calculation, and finally transmits the ciphertext to a third-party organization through the data transmission module.

[0282] The signaling data protection and analysis method provided by this invention implements a metadata-assisted homomorphic encryption and decryption strategy. It generates metadata for each signaling message, which does not contain sensitive information. The data provider establishes a one-to-one correspondence between metadata, plaintext, and encrypted data and stores this information within its system. Data transmitted to third-party organizations contains only metadata and ciphertext, allowing them to more easily identify which data can be batch-processed together. This enables them to complete multiple computational tasks at once, rather than one by one, thus improving computational efficiency. Furthermore, with metadata, the data provider's decryption operation is simplified to a query operation based on the metadata. When a third party requires a specific homomorphic encryption algorithm, it only needs to send the signaling metadata and encryption type back to the data provider. The data provider can then retrieve the plaintext based on the metadata, eliminating the decryption process and significantly improving the system's computational efficiency.

[0283] According to another aspect of the present invention, an apparatus for signaling data protection and analysis is provided, comprising: a memory, a processor, and a signaling data protection and analysis program stored in the memory and executable on the processor, wherein the signaling data protection and analysis program, when executed by the processor, implements the steps of the above-described signaling data protection and analysis method.

[0284] The present invention also provides a computer storage medium.

[0285] The computer storage medium stores a signaling data protection and analysis program, which, when executed by the processor, implements the steps of the aforementioned signaling data protection and analysis method.

[0286] The method implemented when the signaling data protection and analysis program running on the processor is executed can be referred to in various embodiments of the signaling data protection and analysis method of the present invention, and will not be repeated here.

[0287] The present invention also provides a computer program product.

[0288] The computer program product of the present invention includes a signaling data protection and analysis program, which, when executed by a processor, implements the steps of the signaling data protection and analysis method as described above.

[0289] The method implemented when the signaling data protection and analysis program running on the processor is executed can be referred to in various embodiments of the signaling data protection and analysis method of the present invention, and will not be repeated here.

[0290] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0291] The above description is merely an exemplary embodiment of the present invention and is not intended to limit the scope of protection of the present invention, which is determined by the appended claims.

Claims

1. A method for signaling data protection and analysis, comprising the following steps: S1. Data collection: Obtain raw signaling data from the data source, input raw signaling data, collect data through socket API calls, database queries or other data interfaces, and output structured signaling data. S2. Data preprocessing: The structured signaling data is cleaned and formatted. Data cleaning algorithms and data transformation methods are used to de-identify the calling and called numbers, and generate the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC, and the original and derived features of the signaling are output. S3. Metadata generation: Generate metadata for each preprocessed signaling data. Use UUID to encode the metadata for each signaling and save it to a database or distributed storage system. Generate one metadata for each signaling and output a globally unique meaningless metadata code. The metadata contains sensitive information and is globally unique. S4. Hybrid homomorphic encryption: Uses a hybrid homomorphic encryption scheme of Paillier and EIGamal to encrypt or decrypt signaling feature values. Paillier encryption is used by default. If there is a need for re-encryption, the system will switch to the EIGamal encryption scheme according to the re-encryption requirement. S5. Data transmission: Encrypted data and metadata are transmitted to third-party organizations via the socket HTTPS API interface, in the form of metadata plus signaling data ciphertext. S6. Re-encryption Request Notification: When a third-party organization performs statistical analysis on the encrypted data, it directly uses the encrypted data provided by the data provider when performing addition and subtraction operations, as the data provider's default encryption method supports Paillier for addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption request notification service, sending the operation type and metadata back to the data provider. After the data provider restores the plaintext signaling through metadata query, it re-encrypts it with EIGamal and transmits it to the third-party organization through the data transmission module, thus achieving adaptive homomorphic encryption.

2. The method for signaling data protection and analysis as described in claim 1, wherein, In step S4, the signaling feature value is encrypted or decrypted using a hybrid homomorphic encryption scheme of Paillier and EIGamal. The inputs are encryption type, metadata, and plaintext. Specifically, when the encryption type encrypts the preprocessed metadata, Paillier encryption is used, and the output is the Paillier-encrypted ciphertext; when the metadata requiring re-encryption is encrypted, EIGamal encryption is used, and the output is the EIGamal-encrypted ciphertext; the Paillier and EIGamal encryption algorithms are implemented in Java and Python respectively. The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

3. The method for signaling data protection and analysis as described in claim 2, wherein, The Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext, and the Paillier encryption includes the following steps: S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers; S412, Calculate the modulus n and γ n = p × q γ=lcm(p-1,q-1) Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1; S413. Choose an integer g such that gcd(L(g γ mod n 2 ), n)=1, Where L(x) = (x-1) / n, and gcd is the greatest common divisor; S414. Generate a key, which includes a public key and a private key. The public key is (n, g), and the private key is (γ, μ). where μ = L(g γ mod n 2 ) -1 mod n; S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy... gcd(r, n) = 1, Then through c=g M ×r n mod n 2 Calculate the ciphertext; S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal. When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2; In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m2 ×r n mod n 2 ,then c m1-m2 =c m1 ×c m2 mod n 2 , where c m1-m2 It's an encryption of m1-m2. The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

4. The method for signaling data protection and analysis as described in claim 2, wherein, The EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext, and the EIGamal encryption includes the following steps: S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p; S422, Generate key. Private key: randomly select an integer x, 1 <x<p-1; Public key: Calculate y = g x mod p S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1; S424, Calculate c1 and c2 Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2); S425. Perform multiplication or division operations. The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows: C13 = C11 × C12 mod p C23=C21×C22 mod p The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2 ), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps: Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext; the calculation formula is: in, for Encryption; Decrypting the encrypted content involves calculating s: Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

5. A device for signaling data protection and analysis, comprising: The data collection module is used to obtain raw signaling data from the data source, input raw signaling data, collect data through methods including socket API calls, database queries or other data interfaces, and output structured signaling data. The data preprocessing module is used to clean and format the structured signaling data. It uses data cleaning algorithms and data transformation methods to de-identify the calling and called numbers and generate the original and derived features of the signaling. The de-identification of the calling and called numbers is processed using HMAC, and the original and derived features of the signaling are output. The metadata generation module is used to generate metadata for each preprocessed signaling data. It uses UUID to encode the metadata for each signaling and saves it to a database or distributed storage system. It generates one metadata for each signaling and outputs a globally unique meaningless metadata code. The metadata contains sensitive information and is globally unique. The hybrid homomorphic encryption module is used to encrypt or decrypt signaling feature values ​​using a hybrid homomorphic encryption scheme of Paillier and EIGamal. Paillier encryption is used by default; if there is a need for re-encryption, the module will switch to the EIGamal encryption scheme according to the re-encryption requirement. The data transmission module is used to transmit encrypted data and metadata to third-party organizations via the socket HTTPS API interface, in the form of metadata plus signaling data ciphertext. The re-encryption request notification module is used by third-party organizations to perform statistical analysis on encrypted data. When the third-party organization performs addition and subtraction operations on the encrypted data, it directly uses the encrypted data provided by the data provider, because the data provider's default data encryption method supports Paillier, which supports addition and subtraction. When the third-party organization needs to perform multiplication or division on the encrypted data, it calls the data provider's re-encryption request notification service, sending the operation type and metadata back to the data provider. After the data provider restores the plaintext signaling by querying the metadata, it re-encrypts it with EIGamal and transmits it to the third-party organization through the data transmission module, thus achieving adaptive homomorphic encryption.

6. The signaling data protection and analysis apparatus as described in claim 5, wherein, The hybrid homomorphic encryption module uses a Paillier and EIGamal hybrid homomorphic encryption scheme to encrypt or decrypt signaling feature values. The inputs are encryption type, metadata, and plaintext. Specifically, when the encryption type encrypts the preprocessed metadata, Paillier encryption is used, and the output is the Paillier-encrypted ciphertext; when the metadata requiring re-encryption is encrypted, EIGamal encryption is used, and the output is the EIGamal-encrypted ciphertext; the Paillier and EIGamal encryption algorithms are implemented in Java and Python respectively. The decryption operation is performed only on the data provider's side, and the decryption operation is performed directly based on the metadata, without the need for Paillier or EIGamal decryption.

7. The signaling data protection and analysis apparatus as described in claim 6, wherein, The Paillier encryption is used to support homomorphic addition or subtraction operations on ciphertext, and the Paillier encryption includes the following steps: S411. Choose two large prime numbers p and q, where p and q are unequal large prime numbers; S412, Calculate the modulus n and γ n = p × q γ=lcm(p-1,q-1) Where n is the public key, γ is the private key, and lcm is the least common multiple of p-1 and q-1; S413. Choose an integer g such that gcd(L(g γ mod n 2 ), n)=1, Where L(x) = (x-1) / n, and gcd is the greatest common divisor; S414. Generate a key, which includes a public key and a private key. The public key is (n, g), and the private key is (γ, μ). where μ = L(g γ mod n 2 ) -1 mod n; S415. Encryption process: M is the plaintext to be encrypted, and a random integer is selected to satisfy... gcd(r, n) = 1, Then through c=g M ×r n mod n 2 Calculate the ciphertext; S416. Perform operations on the ciphertext. When the operation is addition or subtraction, no decryption is required. When the operation is multiplication or division, the operation type and metadata are sent back to the data provider by calling the data provider's re-encryption request notification service. The data provider then restores the plaintext signaling through the decryption process after querying the metadata and re-encrypts it with EIGamal. When the operation on the ciphertext is addition, there are two ciphertexts c1 and c2, corresponding to plaintexts m1 and m2 respectively. The sum of c1 and c2, c3, is calculated as: c3 = c1 × c2 mod n 2 Decrypting c3 will yield m1+m2; In this case, when the operation on the ciphertext is a subtraction operation, there are two plaintexts m1 and m2, which have already been encrypted using the Paillier encryption algorithm to obtain c. m1 and c m2 To execute m1-m2 on the ciphertext, first find the additive inverse of m2. In the ring modulo n, the additive inverse of m2 is -m2, which can be calculated using -m2 = n-m2. Next, encrypt -m2 to obtain c. -m2 c -m2 =g -m2 ×r n mod n 2 ,then c m1-m2 =c m1 ×c m2 mod n 2 , where c m1-m2 It's an encryption of m1-m2. The decryption process first involves calculating the value of L: L = L(c γ mod n 2 Then, decryption yields the plaintext M = L × μ mod n.

8. The apparatus for signaling data protection and analysis as described in claim 6, wherein, The EIGamal encryption is used to support homomorphic multiplication or division operations on ciphertext. EIGamal encryption includes the following steps: S421. Choose two large prime numbers p and g, where p is a large prime number and g is a primitive root of p; S422, Generate key. Private key: randomly select an integer x, 1 <x<p-1; Public key: Calculate y = g x mod p S423. Encryption process: M is the plaintext to be encrypted, and 0 ≤ M ≤ p. Randomly select an integer k, 1 <k<p-1; S424, Calculate c1 and c2 Where, c1 = g x mod p, c2 = M·y x mod p, the ciphertext C is (c1, c2); S425. Perform multiplication or division operations. The multiplication process on the ciphertext involves two ciphertexts (C11, C21) and (C12, C22), corresponding to plaintexts m1 and m2 respectively. The product of these two ciphertexts (C13, C23) is calculated as follows: C13 = C11 × C12 mod p C23=C21×C22 mod p The division operation on the ciphertext involves two ciphertexts (C1). m1 C2 m1 ) and (C1 m2 C2 m2 ), corresponding to plaintexts m1 and m2 respectively, and executed on the ciphertext. First, find the multiplicative inverse of m2. In the ring of p, this is achieved through the following steps: Where g and h are common parameters of the EIGamal encryption algorithm, and k is a random number, (C1) m1 C2 m1 ) and (C1 m2 C2 m2 Multiplication is used to perform division on the ciphertext; the calculation formula is: in, for Encryption; Decrypting the encrypted content involves calculating s: Calculate s -1 s -1 If s is the multiplicative inverse of s modulo p, then the decryption yields the plaintext M = c²s. -1 mod p.

9. An electronic device, comprising: A memory, a processor, and wherein the memory stores a signaling data protection and analysis program that can run on the processor, the signaling data protection and analysis program, when executed by the processor, implementing the steps of the signaling data protection and analysis method as described in any one of claims 1 to 4.

10. A computer storage medium, wherein, The computer storage medium stores a signaling data protection and analysis program, which, when executed by a processor, implements the steps of the signaling data protection and analysis method as described in any one of claims 1 to 4.

Images