Encryption communication method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides an encrypted communication method and device, equipment, a storage medium and a program product, and relates to the field of financial science and technology. The method comprises the following steps: a coordinator generates an anti-quantum key pair based on a lattice cryptographic algorithm and sends an anti-quantum public key to each participant, each participant encapsulates a session key based on the anti-quantum public key and receives the encapsulated session key sent by each participant, then de-encapsulates the session key by adopting an anti-quantum private key to obtain the session key, and sends the session key to the coordinator. And completing the establishment of an anti-quantum encryption channel between the coordinator and each participant. The participants send encrypted data to the coordinator through the anti-quantum encryption channel, the coordinator analyzes and processes the encrypted data obtained through decryption to obtain a second ciphertext, the second ciphertext is sent to the participants, and business processing is carried out on the data obtained through decryption by the participants. According to the method, a lattice cipher mechanism is introduced to construct a cross-mechanism quantum encryption resistant channel, and the security of data communication is ensured in a quantum computing environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to an encrypted communication method and device, equipment, a storage medium and a program product. BACKGROUND

[0002] With the development of the financial industry, financial subjects such as banks and payment institutions have an increasing demand for cross-border payment, data collaborative modeling and intelligent analysis. For example, through cross-institutional data sharing and analysis, financial institutions can more accurately assess customer demand and customer risk characteristics and other information to improve customer service quality.

[0003] At present, the public key encryption algorithms such as RSA (Rivest-Shamir-Adleman) and ECC (Elliptic Curve Cryptography) widely used by various financial institutions are based on large integer factorization or elliptic curve discrete logarithm problem, and their security depends on classical computing power. However, the Shor algorithm of quantum computing can break the above algorithms in polynomial time, resulting in the risk of encrypted data being broken in the quantum computing era. In addition, although symmetric encryption algorithms have strong anti-quantum ability, key distribution and management still rely on traditional asymmetric encryption protocols, and there is a risk of data leakage.

[0004] Therefore, in the quantum computing environment, the prior art cannot ensure the security of data in the process of data transmission and key exchange. SUMMARY

[0005] The present application provides an encrypted communication method, device, equipment, storage medium and program product to solve the technical problem that the prior art cannot ensure the security of data in the process of data transmission and key exchange in the quantum computing environment.

[0006] In a first aspect, the present application provides an encrypted communication method applied to a coordinator, which comprises:

[0007] generating an anti-quantum key pair based on a lattice cryptography algorithm, the anti-quantum key pair comprising an anti-quantum public key and an anti-quantum private key;

[0008] sending the anti-quantum public key to each participant, so that each participant encapsulates a session key based on the anti-quantum public key;

[0009] receiving the encapsulated session key sent by each participant, and using the anti-quantum private key to decapsulate the encapsulated session key to obtain the session key corresponding to each participant, thereby completing the establishment of an anti-quantum encrypted channel between the coordinator and each participant, so that when the participant transmits encrypted data through the anti-quantum encrypted channel, the encrypted data is encrypted through the anti-quantum encrypted channel to obtain first ciphertext.

[0010] The receiving participant receives the first ciphertext sent by the participating party through the anti-quantum encryption channel, and decrypts the first ciphertext using the session key corresponding to the participating party to obtain encrypted data of the participating party;

[0011] The encrypted data is analyzed and processed to obtain second ciphertext, and the second ciphertext is sent to each participating party through the anti-quantum encryption channel, and the second ciphertext is decrypted by each participating party, and based on the obtained data, business processing is performed.

[0012] In a possible implementation, the receiving participant receives the first ciphertext sent by the participating party through the anti-quantum encryption channel, and decrypts the first ciphertext using the session key corresponding to the participating party to obtain encrypted data of the participating party, comprising:

[0013] The receiving participant receives the first ciphertext sent by the participating party, and decrypts the first ciphertext based on the session key of the participating party to obtain encrypted data and an authentication code, the authentication code being generated by inputting the session key and the first ciphertext into a message authentication code algorithm;

[0014] Based on the session key corresponding to the participating party and the encrypted data, a to-be-verified code is generated, and the consistency of the to-be-verified code and the authentication code is verified;

[0015] In the case that the to-be-verified code and the authentication code are inconsistent, the first ciphertext is discarded, and a security alarm is triggered.

[0016] In a possible implementation, the above-mentioned participating party is multiple, the above-mentioned encrypted data is obtained by homomorphic encryption of the participating party to the original data, the above-mentioned first ciphertext is obtained by encryption of the participating party to the encrypted data through the anti-quantum encryption channel, and the above-mentioned original data is a model parameter variable obtained by training of the participating party to an initial model; The method further comprises:

[0017] In the case that the to-be-verified code and the authentication code are consistent, the encrypted data sent by the multiple participating parties is aggregated and processed to obtain second ciphertext;

[0018] The second ciphertext is encrypted through the anti-quantum encryption channel, and the encrypted second ciphertext is sent to each participating party, and the participating party decrypts the received encrypted second ciphertext based on the session key, and homomorphic decrypts the obtained second ciphertext to obtain the first model parameter variable trained by the multiple participating parties, to update the model parameter of the initial model after training using the first model parameter variable, until the model converges.

[0019] In a possible implementation, the above-mentioned encrypted data includes homomorphic encrypted model parameter variables, and the aggregation and processing of the encrypted data sent by the multiple participating parties to obtain second ciphertext comprises:

[0020] The second ciphertext is obtained by aggregating multiple homomorphically encrypted model parameter variables. The aggregation process includes weighted averaging.

[0021] Secondly, this application provides an encrypted communication method applied to participating parties, the method comprising:

[0022] Receive the quantum-resistant public key sent by the coordinator, who generates a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key.

[0023] Generate a session key and encapsulate it based on the aforementioned quantum-resistant public key;

[0024] The encapsulated session key is sent to the coordinator, so that the coordinator can use a quantum-resistant private key to decapsulate the encapsulated session key and obtain the session key corresponding to the participant, thus completing the establishment of a quantum-resistant encrypted channel between the participant and the coordinator.

[0025] The encrypted data is encrypted through a quantum-resistant encryption channel to obtain the first ciphertext, which is then sent to the coordinator. The coordinator then uses the session key corresponding to each participant to decrypt the first ciphertext and obtain the encrypted data. The coordinator analyzes and processes the encrypted data from multiple participants, and then encrypts the resulting second ciphertext through the quantum-resistant encryption channel and sends it to each participant.

[0026] The system receives the encrypted second ciphertext sent by the coordinator, decrypts the encrypted second ciphertext based on the session key to obtain the second ciphertext, performs decryption processing on the second ciphertext, and performs business processing based on the obtained data.

[0027] In one possible implementation, the encrypted data is encrypted using a quantum-resistant encryption channel to obtain a first ciphertext, which is then sent to the coordinator, including:

[0028] The session key and encrypted data are input into the message authentication code algorithm to generate an authentication code. This authentication code is used by the coordinator to authenticate the participants and to verify the integrity of the encrypted data.

[0029] The encrypted data and authentication code are encrypted using a quantum-resistant encryption channel to obtain the first ciphertext, which is then sent to the coordinator. The coordinator generates a verification code based on the session key and encrypted data of the participating party and verifies the consistency between the verification code and the authentication code.

[0030] In one possible implementation, there are multiple participants. Before encrypting the encrypted data through a quantum-resistant encryption channel to obtain the first ciphertext and sending the first ciphertext to the coordinator, the method further includes:

[0031] The original data is homomorphically encrypted to obtain encrypted data, which is the model parameter variable obtained by the participants after training the initial model;

[0032] After receiving the encrypted second ciphertext sent by the coordinator, decrypting the encrypted second ciphertext based on the session key to obtain the second ciphertext, the method further includes:

[0033] Homomorphic decryption of the second ciphertext yields the parameter variables of the first model, which is collaboratively trained by multiple participants.

[0034] The model parameters of the initial model after training are updated using the first model parameter variables. If the initial model does not converge, the initial model is iteratively trained through a quantum-resistant encrypted channel and collaborative training by multiple participants until the model converges.

[0035] In one possible implementation, the method further includes:

[0036] Obtain the operation log, which includes: timestamp, public key digest, private key digest, and operation digest;

[0037] Write the operation log to the blockchain and restrict the log modification permission through smart contract rules;

[0038] The operation logs on the blockchain are verified for compliance based on a preset period, and the compliance verification results are sent to the audit system.

[0039] Thirdly, this application provides an encrypted communication device for use by a coordinating party, the device comprising:

[0040] The first generation module is used to generate quantum-resistant key pairs based on lattice cryptography algorithms. The quantum-resistant key pairs include a quantum-resistant public key and a quantum-resistant private key.

[0041] The first sending module is used to send the quantum-resistant public key to each participant, so that each participant can encapsulate the session key based on the quantum-resistant public key;

[0042] The first receiving module is used to receive the encapsulated session keys sent by each participating party;

[0043] The decapsulation module is used to decapsulate the encapsulated session key using a quantum-resistant private key to obtain the session key corresponding to each participant. This completes the establishment of a quantum-resistant encryption channel between the coordinator and each participant, enabling participants to encrypt encrypted data through the quantum-resistant encryption channel when transmitting encrypted data, thus obtaining the first ciphertext.

[0044] The first receiving module is also used to receive the first ciphertext sent by the participants through a quantum-resistant encryption channel;

[0045] The first decryption module is used to decrypt the first ciphertext using the session key corresponding to the participant to obtain the participant's encrypted data;

[0046] The first processing module is used to analyze and process the encrypted data to obtain the second ciphertext;

[0047] The first sending module is also used to send the second ciphertext to each participant through a quantum-resistant encryption channel, so that each participant can decrypt the second ciphertext and perform business processing based on the obtained data.

[0048] In one possible implementation, the above-mentioned device further includes: a verification module;

[0049] The first decryption module is specifically used to receive the first ciphertext sent by the participant, and decrypt the first ciphertext based on the participant's session key to obtain encrypted data and an authentication code. The authentication code is generated by inputting the session key and the first ciphertext into the message authentication code algorithm.

[0050] The verification module is used to generate a verification code based on the session key and encrypted data corresponding to the participants, and to verify the consistency between the verification code and the authentication code.

[0051] The first processing module is also used to discard the first ciphertext and trigger a security alarm if the verification code and the authentication code do not match.

[0052] In one possible implementation, there are multiple participants, the encrypted data is obtained by the participants homomorphically encrypting the original data, the first ciphertext is obtained by the participants encrypting the encrypted data through a quantum-resistant encryption channel, and the original data is the model parameter variables obtained by the participants after training the initial model; the device further includes: a first encryption module.

[0053] The first processing module is specifically used to aggregate encrypted data sent by multiple participants to obtain the second ciphertext when the verification code and the authentication code are consistent.

[0054] The first encryption module is used to encrypt the second ciphertext through a quantum-resistant encryption channel and send the encrypted second ciphertext to each participant. The participants decrypt the received encrypted second ciphertext based on the session key and perform homomorphic decryption on the obtained second ciphertext to obtain the first model parameter variables that are jointly trained by multiple participants. The model parameters of the initial model after training are updated using the first model parameter variables until the model reaches convergence.

[0055] In one possible implementation, the first ciphertext includes: encrypted data including: homomorphically encrypted model parameter variables; a first processing module specifically used to aggregate multiple homomorphically encrypted model parameter variables to obtain the second ciphertext; the aggregation processing includes: weighted average processing.

[0056] Fourthly, this application provides an encrypted communication device for use by participating parties, the device comprising:

[0057] The second receiving module is used to receive the quantum-resistant public key sent by the coordinator, which generates a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key.

[0058] The second generation module is used to generate the session key and encapsulate the session key based on the quantum-resistant public key;

[0059] The second sending module is used to send the encapsulated session key to the coordinator, so that the coordinator can use the quantum-resistant private key to decapsulate the encapsulated session key, obtain the session key corresponding to the participant, and complete the establishment of the quantum-resistant encrypted channel between the participant and the coordinator.

[0060] The second encryption module is used to encrypt the encrypted data through a quantum-resistant encryption channel to obtain the first ciphertext;

[0061] The second sending module is also used to send the first ciphertext to the coordinator, so that the coordinator can decrypt the first ciphertext using the session key corresponding to the participant to obtain encrypted data, and analyze and process the encrypted data of multiple participants, and encrypt the obtained second ciphertext through a quantum-resistant encryption channel and send it to each participant.

[0062] The second sending module is also used to receive the encrypted second ciphertext sent by the coordinator;

[0063] The second decryption module is used to decrypt the encrypted second ciphertext based on the session key to obtain the second ciphertext, and then perform business processing based on the obtained data.

[0064] In one possible implementation, the above-mentioned device further includes: a second input module;

[0065] The second input module is used to input the session key and encrypted data into the message authentication code algorithm to generate an authentication code. This authentication code is used by the coordinator to authenticate the participants and to verify the integrity of the encrypted data.

[0066] The second encryption module is specifically used to encrypt the encrypted data and authentication code through a quantum-resistant encryption channel to obtain the first ciphertext, and then send the first ciphertext to the coordinator. The coordinator generates a verification code based on the session key and encrypted data of the participating party, and verifies the consistency between the verification code and the authentication code.

[0067] In one possible implementation, there are multiple participants, and the device further includes a training module;

[0068] The second encryption module is also used to perform homomorphic encryption on the original data to obtain encrypted data, which is the model parameter variables obtained by the participants after training the initial model;

[0069] The second decryption module is specifically used to perform homomorphic decryption on the second ciphertext to obtain the first model parameter variables trained collaboratively by multiple participants.

[0070] The training module is used to update the model parameters of the initial model after training using the first model parameter variables, and to iteratively train the initial model after training through a quantum-resistant encrypted channel and collaborative training by multiple participants until the model converges, provided that the initial model has not yet converged.

[0071] In one possible implementation, the above-mentioned apparatus further includes: an acquisition module, a second processing module, and a verification module;

[0072] The acquisition module is used to acquire operation logs, which include: timestamp, public key digest, private key digest, and operation digest;

[0073] The second processing module is used to write operation logs to the blockchain and restrict log modification permissions through smart contract rules.

[0074] The verification module is used to perform compliance verification on the operation logs on the blockchain based on a preset period and send the compliance verification results to the audit system.

[0075] Fifthly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0076] The aforementioned memory stores instructions executed by the computer;

[0077] The processor executes computer execution instructions stored in the memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0078] In a sixth aspect, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0079] In a seventh aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0080] The encrypted communication method, apparatus, device, storage medium, and program product provided in this application, wherein the coordinator generates a quantum-resistant key pair based on a lattice cryptography algorithm and sends the quantum-resistant public key to each participant, so that each participant generates a session key before the session and encapsulates the session key based on the aforementioned quantum-resistant public key, and then sends the encapsulated session key to the coordinator. After receiving the encapsulated session key, the coordinator uses a quantum-resistant private key to decapsulate the encapsulated session key to obtain the session key corresponding to each participant, thus completing the establishment of a quantum-resistant encrypted channel between the coordinator and each participant. This enables the transmission of data and key exchange in the encrypted channel to resist quantum computing attacks and ensure the integrity and immutability of the transmitted data.

[0081] Furthermore, the participants encrypt the data using a quantum-resistant encryption channel to obtain a first ciphertext, which is then sent to the coordinator. The coordinator decrypts the first ciphertext using the participant's corresponding session key to obtain encrypted data. The coordinator then analyzes and processes the encrypted data to obtain a second ciphertext, which is subsequently encrypted again using the quantum-resistant encryption channel. This second ciphertext is then sent to each participant, who decrypts it using their session key to obtain the second ciphertext. The coordinator then uses this second ciphertext for business processing. In this method, the entire communication link, from key negotiation to data transmission, is built on lattice cryptography, possessing resistance to quantum attacks and ensuring communication security. Attached Figure Description

[0082] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0083] Figure 1 An interactive illustration of an encrypted communication method provided in this application embodiment. Figure 1 ;

[0084] Figure 2 An interactive illustration of an encrypted communication method provided in this application embodiment. Figure 2 ;

[0085] Figure 3 Schematic diagram of the structure of an apparatus for an encrypted communication method provided in this application Figure 1 ;

[0086] Figure 4 Schematic diagram of the structure of an apparatus for an encrypted communication method provided in this application Figure 2 ;

[0087] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0088] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0089] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of the relevant data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation access points for users to choose to authorize or refuse.

[0091] Furthermore, the technical solution involved in this application, which involves big data analysis of user information (including but not limited to personal biometrics, identity data, consumption data, asset data, electronic terminal operation data, etc.) and the use of artificial intelligence technology for automated decision-making, and makes decisions that have a significant impact on personal rights based on the results of automated decision-making, provides users with corresponding operation entry points for users to choose to agree to or reject the results of automated decision-making; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0092] It should be noted that the encrypted communication methods, devices, equipment, storage media and program products provided in this application can be used in the field of financial technology, or in any field other than financial technology. The application fields of the encrypted communication methods, devices, equipment, storage media and program products in this application are not limited.

[0093] Cross-institutional data sharing is involved in scenarios such as cross-border payments, joint bank modeling, and federated learning collaborative modeling. Cross-border payments require compliant data transfer; that is, when banks and payment institutions transmit user information in cross-border transactions, they must meet relevant regulatory requirements, ensuring that data is transferred in an encrypted state and does not violate the principle of data sovereignty. Joint bank modeling and intelligent analysis require financial institutions to jointly train risk control models, anti-fraud models, etc., through federated learning technology without sharing raw data, in order to improve model accuracy and avoid the risk of data leakage.

[0094] Currently, public-key encryption algorithms such as RSA and ECC, widely used by financial institutions, are based on large integer factorization or elliptic curve discrete logarithm problems, and their security relies on classical computing power. However, Shor's algorithm in quantum computing can break these algorithms in polynomial time, posing a risk of encrypted data being compromised in the quantum computing era. Furthermore, while symmetric encryption algorithms such as AES (Advanced Encryption Standard) possess strong quantum resistance, key distribution and management still rely on traditional asymmetric encryption protocols, posing a risk of data leakage.

[0095] Therefore, in a quantum computing environment, existing technologies cannot ensure the security of data during data transmission and key exchange.

[0096] The encrypted communication method provided in this application involves a coordinator generating a quantum-resistant key pair based on a lattice cryptography algorithm and sending the quantum-resistant public key to each participating party. This allows each participating party to generate a session key before the session and encapsulate it based on the aforementioned quantum-resistant public key. The encapsulated session key is then sent to the coordinator. Upon receiving the encapsulated session key, the coordinator uses a quantum-resistant private key to decapsulate it, obtaining the session key corresponding to each participating party. This establishes a quantum-resistant encrypted channel between the coordinator and each participating party, enabling data transmission and key exchange within this encrypted channel to resist quantum computing attacks and ensuring the integrity and immutability of the transmitted data.

[0097] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0098] Figure 1 An interactive illustration of an encrypted communication method provided in this application embodiment. Figure 1The interactive entities in this method include a coordinator and at least one participant. Participants may include financial institutions such as banks and securities firms, while coordinators may include UnionPay Cloud and third-party trusted cloud service platforms. This method can be applied to scenarios such as cross-border payments, joint bank modeling, and federated learning collaborative modeling. Figure 1 As shown, the method includes:

[0099] S101, The coordinator generates quantum-resistant key pairs based on lattice cryptography algorithm.

[0100] Among them, quantum-resistant key pairs include quantum-resistant public keys and quantum-resistant private keys.

[0101] Lattice cryptography constructs lattice-based mathematical problems whose computational complexity grows exponentially in both classical and quantum computing environments, thus effectively resisting quantum computing attacks. This step generates quantum-resistant key pairs based on lattice cryptography algorithms, which can also be replaced by other quantum-resistant algorithms such as hash-based signature algorithms.

[0102] This method effectively avoids the risk that existing public-key encryption algorithms can be cracked by quantum algorithms in a quantum computing environment, which could lead to cross-institutional communication data being eavesdropped or tampered with under quantum computing attacks.

[0103] S102. The coordinator sends the quantum-resistant public key to each participant.

[0104] There is at least one participant, and the coordinator distributes the quantum-resistant public key to each participant.

[0105] For example, in a cross-border payment scenario, there is only one participant, which could be an overseas receiving bank or payment gateway. The coordinating party could be a domestic bank or cross-border clearing institution initiating the transfer. The cross-border clearing institution packages the quantum-resistant public key as part of the business data into a payment initialization message and sends the data packet to the participant. In this scenario, the cross-border clearing institution can also send the quantum-resistant public key to the participant's payment gateway via a trusted financial communication network. This application does not impose any limitations on this.

[0106] In a federated learning collaborative modeling scenario, there are multiple participants, such as multiple banks, and the coordinator could be UnionPay Cloud. UnionPay Cloud distributes quantum-resistant public keys to multiple banks via broadcast signaling at the start of each training task.

[0107] S103. The participants generate a session key and encapsulate the session key based on a quantum-resistant public key.

[0108] Participants generate session keys based on their business needs, and then encapsulate these session keys using the coordinator's quantum-resistant public key. The business needs require a session with the coordinator.

[0109] Optionally, before the session, the participants trigger a session key generation mechanism, inputting the coordinator's quantum-resistant public key into a key encapsulation algorithm. The algorithm then performs a transformation to obtain the encapsulated session key. The key encapsulation algorithm can be, for example, KEM (Key Encapsulation Mechanism). In this case, the session key is a symmetric key encapsulated based on the coordinator's quantum-resistant public key obtained by executing the KEM mechanism, ensuring that sensitive information is not exposed during the key exchange process.

[0110] S104. The participating parties send the encapsulated session key to the coordinator.

[0111] The participating parties send the encapsulated session key to the coordinator via a trusted financial communication network. This encapsulated session key is obtained based on a quantum-resistant public-key cryptography and key encapsulation mechanism, thus resisting quantum attacks during transmission and ensuring the security of the session key.

[0112] S105. The coordinator uses a quantum-resistant private key to decapsulate the encapsulated session key, obtaining the session key corresponding to each participant, thus completing the establishment of a quantum-resistant encrypted channel between the coordinator and each participant.

[0113] Different participants generate different session keys. For multiple coordinators, each participant's encapsulated session key is decapsulated using their own quantum-resistant private key to obtain multiple participants' session keys. In subsequent sessions with multiple participants, the corresponding session keys are used to encrypt data, thereby establishing a quantum-resistant encrypted channel between the coordinator and each participant.

[0114] Understandably, after receiving the encapsulated session key, the coordinator calls the lattice cryptography's decapsulation function and uses its quantum-resistant private key to decrypt the encapsulated session key, thus restoring the session key of the participating party.

[0115] This step enables cross-institutional communication to maintain the confidentiality and integrity of data even under the threat of quantum computing.

[0116] S106. The participants encrypt the encrypted data through a quantum-resistant encryption channel to obtain the first ciphertext.

[0117] The encrypted data is obtained by the participants encrypting the business data and then sending the encrypted data to the coordinator through a quantum-resistant encryption channel. Since the coordinator lacks the private key for decrypting the encrypted data and the context of the original business data, it cannot deduce the business data based on the encrypted data. Therefore, the risk of data leakage at the coordinator is avoided.

[0118] When transmitting encrypted data through a quantum-resistant encrypted channel, each participant encrypts the data using its session key to obtain the first ciphertext, ensuring security during data transmission. This step employs a dual encryption mechanism to encrypt and transmit business data, thereby enhancing data security.

[0119] Understandably, the encryption algorithms involved in this step include, but are not limited to, homomorphic encryption and secure multi-party computation. The aforementioned business data may, for example, be credit risk indicators or model parameter gradients.

[0120] S107. The participating parties send the first ciphertext to the coordinator.

[0121] S108. The coordinating party uses the session key corresponding to the participating party to decrypt the first ciphertext, obtains the encrypted data, and analyzes and processes the encrypted data to obtain the second ciphertext.

[0122] The coordinator stores a session key mapping table, which includes the mapping relationship between session keys and participant identities / communication connection handles.

[0123] After receiving the first ciphertext, the coordinator queries the corresponding session key from the session key mapping table based on the identity identifier or communication connection handle corresponding to the first ciphertext, and then decrypts the first ciphertext based on the session key to obtain the encrypted data.

[0124] For example, when a participant sends the first ciphertext to the coordinator, the data packet includes the participant's identity identifier. After receiving the data packet containing the first ciphertext, the coordinator parses the data packet to obtain the identity identifier, looks up the session key corresponding to the identity identifier in the aforementioned session key mapping table, and then uses the session key to decrypt the first ciphertext to obtain the encrypted data.

[0125] The aforementioned analysis and processing of encrypted data includes, but is not limited to, compliance verification, aggregation, statistics, and feature extraction. For example, in cross-border payment scenarios, the coordinating party needs to perform compliance screening and risk aggregation analysis on the encrypted data to obtain a second ciphertext. The plaintext data of this second ciphertext may include, for example, the comprehensive risk score and compliance verification results of this cross-border payment transaction.

[0126] S109. The coordinator encrypts the second ciphertext through a quantum-resistant encryption channel.

[0127] When the coordinator sends the second ciphertext to each participant, it uses each participant's corresponding session key to encrypt the second ciphertext, and then sends the encrypted second ciphertext to the corresponding participant. For example, the first participant's first session key is used to encrypt the second ciphertext, resulting in ciphertext one, which is then sent to the first participant. The second participant's second session key is used to encrypt the second ciphertext, resulting in ciphertext two, which is then sent to the second participant.

[0128] S110, The coordinator sends the encrypted second ciphertext to each participant.

[0129] S111. The participating party decrypts the encrypted second ciphertext based on the session key to obtain the second ciphertext, and then decrypts the second ciphertext to perform business processing based on the obtained data.

[0130] After receiving the encrypted second ciphertext from the coordinator, each participating party decrypts it using its session key to obtain the second ciphertext. The document explains how the participating party decrypts this second ciphertext and obtains the data. It also provides examples of what the second ciphertext is, what data is obtained, and what business operations are performed accordingly.

[0131] The encrypted communication method provided in this embodiment includes a coordinator and at least one participant. First, the coordinator generates a quantum-resistant key pair based on a lattice cryptography algorithm and sends the quantum-resistant public key to each participant. This allows each participant to generate a session key before the session and encapsulate it using the aforementioned quantum-resistant public key. The encapsulated session key is then sent to the coordinator. Upon receiving the encapsulated session key, the coordinator decapsulates it using a quantum-resistant private key to obtain the session key corresponding to each participant. This establishes a quantum-resistant encrypted channel between the coordinator and each participant. This ensures that data transmission and key exchange within this encrypted channel are resistant to quantum computing attacks, guaranteeing the integrity and immutability of the transmitted data. Furthermore, the method's encapsulation of the session key using the quantum-resistant public key further enhances its resistance to quantum attacks during transmission, ensuring the security of the session key.

[0132] Furthermore, the participants encrypt the data using a quantum-resistant encryption channel to obtain the first ciphertext, which is then sent to the coordinator. The coordinator decrypts the first ciphertext using the participant's corresponding session key to obtain the encrypted data. This encrypted data is then analyzed and processed to obtain the second ciphertext, which is subsequently encrypted again using the quantum-resistant encryption channel. The encrypted second ciphertext is then sent to each participant, who decrypts it using their session key to obtain the second ciphertext. The second ciphertext is then decrypted, and business processing is performed based on the obtained data. This method, from key negotiation to data transmission, uses lattice cryptography to construct the entire communication link, possessing quantum attack resistance and ensuring communication security. Moreover, this method does not directly send data to the coordinator via the quantum-resistant encryption channel; instead, it encrypts the data and sends the encrypted data to the coordinator via the same channel, avoiding the risk of data leakage at the coordinator's location.

[0133] Figure 2 An interactive illustration of an encrypted communication method provided in this application embodiment. Figure 1 This method is in Figure 2 Based on the embodiments, such as Figure 3 As shown, after constructing the quantum-resistant encrypted channel between the coordinator and multiple participants, a possible encrypted communication method is described in detail using the training of a multi-participant collaborative model as a real-time scenario. This method includes:

[0134] S201. The participants perform homomorphic encryption on the original data to obtain encrypted data.

[0135] The raw data described above represents the model parameter variables obtained by the participants after training the initial model. The initial model is distributed to each participant by the coordinator, and each participant trains the initial model on their local dataset. For example, after one round of iterative training, the current model parameters are obtained, and the model parameter variables are calculated. One training round can, for example, consist of 10 iterations, the number of iterations depending on the training requirements. Furthermore, the update amount can be the difference between the current model parameters obtained after the current training round and the initial model parameters, or it can be the gradient calculated during training.

[0136] Data transmission between the participating parties and the coordinator is conducted via a quantum-resistant encrypted channel. Before data transmission, to ensure the confidentiality and security of the data at the coordinator's location, the participating parties perform homomorphic encryption on the original data. For example, the model parameter variables of participant a are: ΔWa = (ΔWa1, ΔWa2, ..., ΔWan), and the model parameter variables of participant b are: ΔWb = (ΔWb1, ΔWb2, ..., ΔWbn). Here, n is the total number of model parameters, and n is a positive integer. Participant a homomorphically encrypts ΔWa to obtain E_ΔWa = (E_ΔWa1, E_ΔWa2, ..., E_ΔWan), and participant b homomorphically encrypts ΔWb to obtain E_ΔWb = (E_ΔWb1, E_ΔWb2, ..., E_ΔWbn).

[0137] Understandably, the key pair required for homomorphic encryption is generated and managed by the participant's local hardware security module, trusted execution environment, or certified key management service. For example, before sending model parameter variables, the participant sends a key generation request to the certified key management service. This request includes, but is not limited to, the participant's identity identifier, key request identifier, and key metadata, such as key purpose and security level. The key management service authenticates the participant based on the key generation request to confirm whether the participant has the authority to request keys and the participant's legitimacy. If the authentication is successful, the service executes the homomorphic encryption algorithm to generate a homomorphic encryption key pair and distributes this key pair to multiple participants. Each participant then uses the homomorphic public key to encrypt data and the homomorphic private key to decrypt the homomorphic ciphertext.

[0138] For example, in cross-border transactions, a domestic bank initiates a cross-border computing request, triggering a key generation instruction. This instruction is sent to the participating party's HSM (Hardware Security Module), which then generates a single-use homomorphic encryption key pair based on its built-in homomorphic encryption algorithm. In this key pair, the public key is used to encrypt the transaction data, while the private key is securely stored by the HSM.

[0139] This step encrypts the model parameter variables using a homomorphic encryption mechanism, enabling compliant data flow under encryption. Furthermore, the homomorphic encryption of the model parameter variables and the resulting ciphertext are sent to the coordinator via a quantum-resistant encryption channel for aggregation processing, ensuring that cross-institutional model training data remains within its domain and protecting privacy.

[0140] S202. The participants input the session key and encrypted data into the message authentication code algorithm to generate an authentication code; the encrypted data and authentication code are encrypted using quantum-resistant encryption to obtain the first ciphertext.

[0141] The authentication code is used by the coordinator to authenticate the participants and verify the integrity of transmitted data. Message authentication code algorithms include, but are not limited to, the MAC (Message Authentication Code) algorithm. When the MAC algorithm is used, the resulting authentication code is a MAC authentication tag.

[0142] The session key and encrypted data are input into the message authentication code algorithm, which outputs an authentication code. If the encrypted data is modified during transmission, the final calculated authentication code will change drastically.

[0143] For example, if the encrypted data is C_text and the authentication code is MAC, then {C_text, MAC} is treated as a data packet, encrypted to obtain the first ciphertext, and sent to the coordinator.

[0144] S203. The participating party sends the first ciphertext to the coordinator.

[0145] Each participating party encrypts the data packet consisting of the first ciphertext and the authentication code using its own session key, and sends the encrypted data packet to the coordinator to ensure the security of the data packet during transmission.

[0146] S204. The coordinator decrypts the first ciphertext based on the participant's session key to obtain encrypted data and authentication code; generates a verification code based on the participant's corresponding session key and encrypted data, and verifies the consistency between the verification code and the authentication code.

[0147] In step S203, the data packet is associated with the participant's identity identifier. Based on this identifier, the session key corresponding to the participant is obtained from the session key mapping table, and the first ciphertext is decrypted based on the session key to obtain encrypted data and an authentication code. Subsequently, the encrypted data in the data packet and the aforementioned session key are input into the message authentication code algorithm to obtain the verification code.

[0148] The message authentication code algorithm used is the same as that used in step S202 above. Therefore, if the encrypted data is modified during transmission or when it is transmitted to the coordinator, the generated verification code will be inconsistent with the authentication code. Furthermore, since the verification code is generated based on the session key and the encrypted data, and each participant has a different session key, if the data packet originates from an unauthorized participant, the resulting verification code will be inconsistent with the authentication code.

[0149] Therefore, after obtaining the verification code, it is determined whether the authentication code and the verification code are consistent.

[0150] S205. If the verification code and the authentication code do not match, the coordinating party discards the first ciphertext and triggers a security alert.

[0151] For example, if the verification code and the authentication code do not match, the first ciphertext is cleared from the coordinator's cache, and a security event log is generated. This security event log is then sent to the operations and maintenance personnel, and / or an alert message is displayed on the operations and maintenance interface. This alert message includes the aforementioned security event log. The security event log includes, but is not limited to: event type, timestamp of occurrence, identity of the unauthorized party, some metadata of the data packet (such as sequence number, size, etc.), and the first MAC tag received by the coordinator and the calculated second MAC tag. The event type can be, for example, {MAC_VERIFICATION_FAILED}. The “MAC_VERIFICATION_FAILED” indicates that the MAC verification failed.

[0152] S206. If the verification code and the authentication code are consistent, the coordinator aggregates the encrypted data sent by multiple participants to obtain the second ciphertext; the second ciphertext is then encrypted through a quantum-resistant encryption channel.

[0153] If the verification code and the authentication code match, it indicates that the data source is trustworthy, the data has not been altered during transmission, the session key is valid, and both parties have successfully authenticated their identities. Therefore, in the case of encrypted data, the coordinator aggregates the encrypted data sent by multiple participants to obtain the second ciphertext. Since the encrypted data is obtained by encrypting the model parameter variables using a homomorphic encryption mechanism, the encrypted data is directly aggregated, and then the resulting second ciphertext is encrypted and transmitted through a quantum-resistant encryption channel.

[0154] Optionally, the encrypted data includes homomorphically encrypted model parameter variables. A method is provided here to aggregate encrypted data sent by multiple participants to obtain a second ciphertext. This method includes: aggregating multiple homomorphically encrypted model parameter variables to obtain the second ciphertext. The aggregation process includes: weighted averaging. The weight corresponding to each homomorphically encrypted model parameter variable can be determined, for example, based on the amount of data in the participant's training set; the larger the data volume, the larger the weight. Furthermore, when the coordinator performs a weighted average on the homomorphically encrypted model parameter variables, the weighted average is broken down into a combination of addition and multiplication.

[0155] Understandably, in steps S202 to S203, when a participant sends encrypted data to the coordinator, the encrypted data is packaged with multiple metadata items, and then transmitted through a quantum-resistant encryption channel. The metadata items include the participant's data volume.

[0156] S207. The coordinator sends the encrypted second ciphertext to each participant.

[0157] The coordinator retrieves the session keys corresponding to each participant from the session key mapping table, and encrypts the second ciphertext based on multiple session keys to obtain multiple encrypted second ciphertexts. Then, the second ciphertext is encrypted using the first participant's session key and sent to the first participant; similarly, the second ciphertext is encrypted using the second participant's session key and sent to the second participant.

[0158] S208. The participants decrypt the encrypted second ciphertext based on the session key to obtain the second ciphertext; they then perform homomorphic decryption on the second ciphertext to obtain the first model parameter variables for collaborative training by multiple participants.

[0159] As explained in step S201 above, multiple participants each possess a homomorphic private key. Each participant decrypts the second ciphertext based on this homomorphic private key, and the resulting plaintext is the first model parameter variable that the multiple participants are collaboratively training.

[0160] S209. The participants update the model parameters of the initial model after training using the first model parameter variables, and if the initial model does not converge, they iteratively train the initial model after training through a quantum-resistant encrypted channel and collaborative training by multiple participants until the model converges.

[0161] Taking the first participant among multiple participants as an example, the first participant updates the model parameters of the local initial model using the first model parameter variable, and verifies whether the initial model has converged through the local dataset. If it has not converged, the first participant trains the model based on the local training set, uses the obtained second model parameter variable as the original data, and executes steps S201 to S209 to iterate and train the model until the model converges, or the number of iterations reaches the preset maximum number of iterations, ending the current collaborative training.

[0162] Optionally, to meet the audit requirements of the financial industry, ensure the immutability of audit logs, and provide an automated audit mechanism during data transmission, an audit method is provided here. This method includes: acquiring operation logs; writing the operation logs to a blockchain and restricting log modification permissions through smart contract rules; performing compliance verification on the operation logs on the blockchain based on a preset period, and sending the compliance verification results to the audit system. The operation logs include: a timestamp, a public key digest, a private key digest, and an operation digest.

[0163] Optionally, compliance verification includes, but is not limited to: monitoring the encryption status during transmission and processing; for cross-border data, matching data export regulations and verifying whether the encrypted data complies with relevant standards. Furthermore, after obtaining the compliance verification results, the results will be output to a regulatory platform or blockchain auditing system.

[0164] In this method, records of all key operations (such as parameter uploading and model aggregation) are written to the blockchain via smart contracts to ensure data integrity. Furthermore, compliance checks are automatically triggered through compliance verification rules within the smart contracts, reducing manual intervention and improving the efficiency and accuracy of compliance verification. For example, compliance verification rules may stipulate that manual review is required if the number of model aggregations exceeds a certain threshold.

[0165] Regulatory agencies can view logs in real time through blockchain explorers, ensuring transparency and traceability in the data sharing process. This method leverages the distributed nature of blockchain to address the centralized vulnerabilities of traditional auditing mechanisms, while also automating oversight through smart contracts, significantly improving the compliance and credibility of cross-agency data sharing.

[0166] The encrypted communication method provided in this embodiment obtains encrypted data by homomorphically encrypting the original data through the participating parties. The original data consists of model parameter variables obtained by the participating parties after training the initial model. This method introduces a homomorphic encryption mechanism during collaborative training, supporting decryption-free aggregation operations on the encrypted model parameter variables, thus achieving the privacy protection goal of "data remaining within its domain and model being updatable."

[0167] Before constructing the quantum-resistant encrypted channel, the participants generate a session key. This session key, along with the aforementioned encrypted data, is input into a message authentication code algorithm to generate an authentication code. The encrypted data and authentication code are then encrypted using the quantum-resistant encrypted channel to obtain the first ciphertext, which is then sent to the coordinator. The coordinator decrypts the first ciphertext based on the participants' session keys, obtaining the encrypted data and authentication code. Based on the participants' corresponding session keys and encrypted data, the coordinator generates a verification code to verify the consistency between the verification code and the authentication code. This method, by introducing a message authentication code algorithm to verify the consistency between the authentication code and the verification code, achieves a security protection mechanism integrating data integrity verification, data confidentiality verification, and identity authentication. This method not only utilizes the quantum-resistant encrypted channel to ensure the security of data transmission but also verifies the legitimacy of the data source and the integrity of the transmitted content through a verification mechanism.

[0168] If the verification code and the authentication code do not match, the coordinating party discards the first ciphertext and triggers a security alert. This method establishes a proactive defense mechanism, immediately discarding data upon detecting anomalies in received data to prevent the spread of potential attacks. Furthermore, the method promptly triggers security alerts, enabling operations and maintenance personnel to promptly grasp security incidents and perform maintenance.

[0169] If the verification code and the authentication code match, the encrypted data sent by multiple participants are aggregated to obtain the second ciphertext. The second ciphertext is then encrypted through a quantum-resistant encryption channel and sent to each participant. Each participant decrypts the second ciphertext using their session key and performs homomorphic decryption to obtain the first model parameter variables for collaborative training by multiple participants. These first model parameter variables are then used to update the model parameters of the initial model after training. If the initial model does not converge, the initial model is iteratively trained through a quantum-resistant encryption channel and collaborative training by multiple participants until the model converges.

[0170] This method, under the condition that the verification code and the authentication code are consistent, i.e. the identities of the participants and coordinators are correct and the transmitted data is secure, constructs a basic security layer for cross-institutional data sharing by combining a quantum-resistant encryption protocol with a collaborative training mechanism. This ensures communication security, quantum-resistant capability for encrypted transmission and aggregation of model parameters, and enables compliant data flow in an encrypted state through a homomorphic encryption mechanism.

[0171] Figure 3 A schematic diagram of the encrypted communication device provided in this application. Figure 4 As shown, the encrypted communication device 30 provided in this embodiment is applied to the participating parties, and the device includes:

[0172] The first generation module 301 is used to generate a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key.

[0173] The first sending module 302 is used to send the quantum-resistant public key to each participant so that each participant can encapsulate the session key based on the quantum-resistant public key;

[0174] The first receiving module 303 is used to receive the encapsulated session key sent by each participating party;

[0175] The decapsulation module 304 is used to decapsulate the encapsulated session key using a quantum-resistant private key to obtain the session key corresponding to each participant, and to complete the establishment of a quantum-resistant encryption channel between the coordinator and each participant. This enables the participants to encrypt the encrypted data through the quantum-resistant encryption channel when transmitting encrypted data, thereby obtaining the first ciphertext.

[0176] The first receiving module 303 is also used to receive the first ciphertext sent by the participants through the quantum-resistant encryption channel;

[0177] The first decryption module 305 is used to decrypt the first ciphertext using the session key corresponding to the participant to obtain the participant's encrypted data;

[0178] The first processing module 306 is used to analyze and process the encrypted data to obtain the second ciphertext;

[0179] The first sending module 302 is also used to send the second ciphertext to each participant through a quantum-resistant encryption channel, so that each participant can decrypt the second ciphertext and perform business processing based on the obtained data.

[0180] In one possible implementation, the above-mentioned device further includes: a verification module 307;

[0181] The first decryption module 305 is specifically used to receive the first ciphertext sent by the participant, and decrypt the first ciphertext based on the participant's session key to obtain encrypted data and an authentication code. The authentication code is generated by inputting the session key and the first ciphertext into the message authentication code algorithm.

[0182] The verification module 307 is used to generate a verification code based on the session key and encrypted data corresponding to the participants, and to verify the consistency between the verification code and the authentication code.

[0183] The first processing module 306 is also used to discard the first ciphertext and trigger a security alarm if the verification code and the authentication code are inconsistent.

[0184] In one possible implementation, there are multiple participants, the encrypted data is obtained by the participants homomorphically encrypting the original data, the first ciphertext is obtained by the participants encrypting the encrypted data through a quantum-resistant encryption channel, and the original data is the model parameter variables obtained by the participants after training the initial model; the device further includes: a first encryption module 308.

[0185] The first processing module 306 is specifically used to aggregate encrypted data sent by multiple participants to obtain the second ciphertext when the verification code and the authentication code are consistent.

[0186] The first encryption module 308 is used to encrypt the second ciphertext through a quantum-resistant encryption channel and send the encrypted second ciphertext to each participant. The participants decrypt the received encrypted second ciphertext based on the session key and perform homomorphic decryption on the obtained second ciphertext to obtain the first model parameter variables trained by multiple participants. The first model parameter variables are used to update the model parameters of the initial model after training until the model reaches convergence.

[0187] In one possible implementation, the encrypted data includes: homomorphically encrypted model parameter variables; a first processing module 306 is specifically used to aggregate multiple homomorphically encrypted model parameter variables to obtain a second ciphertext; the aggregation processing includes: weighted average processing.

[0188] The encrypted communication device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0189] Figure 4 A schematic diagram of the encrypted communication device provided in this application. Figure 5 As shown, the encrypted communication device 40 provided in this embodiment is applied to the participating parties, and the device includes:

[0190] The second receiving module 401 is used to receive the quantum-resistant public key sent by the coordinator, which generates a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key.

[0191] The second generation module 402 is used to generate a session key and encapsulate the session key based on a quantum-resistant public key;

[0192] The second sending module 403 is used to send the encapsulated session key to the coordinator, so that the coordinator can use the quantum-resistant private key to decapsulate the encapsulated session key, obtain the session key corresponding to the participant, and complete the establishment of the quantum-resistant encrypted channel between the participant and the coordinator.

[0193] The second encryption module 404 is used to encrypt the encrypted data through a quantum-resistant encryption channel to obtain the first ciphertext;

[0194] The second sending module 403 is also used to send the first ciphertext to the coordinator so that the coordinator can decrypt the first ciphertext using the session key corresponding to the participant to obtain encrypted data, and analyze and process the encrypted data of multiple participants, and encrypt the obtained second ciphertext through a quantum-resistant encryption channel and send it to each participant.

[0195] The second sending module 403 is also used to receive the encrypted second ciphertext sent by the coordinator;

[0196] The second decryption module 405 is used to decrypt the encrypted second ciphertext based on the session key to obtain the second ciphertext, and then perform business processing based on the obtained data.

[0197] In one possible implementation, the above-mentioned device further includes: a second input module 406;

[0198] The second input module 406 is used to input the session key and encrypted data into the message authentication code algorithm to generate an authentication code. This authentication code is used by the coordinator to authenticate the participants and to verify the integrity of the encrypted data.

[0199] The second encryption module 404 is specifically used to encrypt the encrypted data and authentication code through a quantum-resistant encryption channel to obtain the first ciphertext, and send the obtained first ciphertext to the coordinator. The coordinator generates a verification code based on the session key and encrypted data corresponding to the participants, and verifies the consistency between the verification code and the authentication code.

[0200] In one possible implementation, there are multiple participants, and the device further includes a training module 407.

[0201] The second encryption module 404 is also used to perform homomorphic encryption on the original data to obtain encrypted data, which is the model parameter variables obtained by the participants after training the initial model;

[0202] The second decryption module 405 is specifically used to perform homomorphic decryption on the second ciphertext to obtain the first model parameter variables trained collaboratively by multiple participants.

[0203] The training module 407 is used to update the model parameters of the initial model after training using the first model parameter variables, and to iteratively train the initial model after training through a quantum-resistant encrypted channel and collaborative training by multiple participants until the model converges, provided that the initial model has not yet converged.

[0204] In one possible implementation, the above-mentioned device further includes: an acquisition module 408, a second processing module 409, and a verification module 410;

[0205] The acquisition module 408 is used to acquire the operation log, which includes: timestamp, public key digest, private key digest and operation digest;

[0206] The second processing module 409 is used to write the operation log to the blockchain and restrict the log modification permission through smart contract rules.

[0207] The verification module 410 is used to perform compliance verification on the operation logs on the blockchain based on a preset period and send the compliance verification results to the audit system.

[0208] The encrypted communication device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0209] Figure 5 A schematic diagram of the structure of the electronic device provided in this application. ​ As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0210] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0211] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0212] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0213] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0214] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0215] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0216] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0217] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0218] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0219] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0220] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0221] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0222] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0223] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0224] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0225] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0226] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0227] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0228] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0229] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0230] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0231] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0232] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An encrypted communication method, characterized in that, Applied to the coordinating party, the method includes: Quantum-resistant key pairs are generated based on lattice cryptography algorithms, wherein the quantum-resistant key pairs include a quantum-resistant public key and a quantum-resistant private key; The quantum-resistant public key is sent to each participant so that each participant can encapsulate the session key based on the quantum-resistant public key; The coordinator receives the encapsulated session key sent by each of the participating parties and decapsulates the encapsulated session key using the quantum-resistant private key to obtain the session key corresponding to each participating party. This completes the establishment of a quantum-resistant encryption channel between the coordinator and each of the participating parties, so that when the participating party transmits encrypted data through the quantum-resistant encryption channel, the encrypted data is encrypted through the quantum-resistant encryption channel to obtain the first ciphertext. The first ciphertext sent by the participant through the quantum-resistant encryption channel is received, and the first ciphertext is decrypted using the session key corresponding to the participant to obtain the participant's encrypted data. The encrypted data is analyzed and processed to obtain a second ciphertext, which is then sent to each participating party through the quantum-resistant encryption channel. Each participating party decrypts the second ciphertext and performs business processing based on the obtained data.

2. The method according to claim 1, characterized in that, The step of receiving the first ciphertext sent by the participant through the quantum-resistant encryption channel and decrypting the first ciphertext using the session key corresponding to the participant to obtain the participant's encrypted data includes: The system receives the first ciphertext sent by the participant and decrypts the first ciphertext based on the participant's session key to obtain the encrypted data and the authentication code. The authentication code is generated by inputting the session key and the encrypted data into a message authentication code algorithm. A verification code is generated based on the session key corresponding to the participating party and the encrypted data, and the consistency between the verification code and the authentication code is verified. If the verification code and the authentication code do not match, the first ciphertext is discarded and a security alarm is triggered.

3. The method according to claim 2, characterized in that, The participants are multiple, and the encrypted data is obtained by the participants homomorphically encrypting the original data. The first ciphertext is obtained by the participants encrypting the encrypted data through the quantum-resistant encryption channel. The original data is the model parameter variables obtained by the participants after training the initial model. The method further includes: If the verification code and the authentication code match, the encrypted data sent by multiple participants are aggregated to obtain the second ciphertext. The second ciphertext is encrypted through the quantum-resistant encryption channel and sent to each of the participating parties. The participating parties decrypt the received second ciphertext based on the session key and perform homomorphic decryption on the obtained second ciphertext to obtain the first model parameter variables for collaborative training by multiple participating parties. The model parameters of the initial model after training are updated using the first model parameter variables until the model converges.

4. The method according to claim 3, characterized in that, The encrypted data includes: homomorphically encrypted model parameter variables. The aggregation of encrypted data sent by multiple participants to obtain the second ciphertext includes: The multiple homomorphically encrypted model parameter variables are aggregated to obtain the second ciphertext. The aggregation process includes weighted averaging.

5. An encrypted communication method, characterized in that, Applied to participating parties, the method includes: The system receives a quantum-resistant public key sent by a coordinator, who generates a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key. Generate a session key and encapsulate the session key based on the quantum-resistant public key; The encapsulated session key is sent to the coordinator, so that the coordinator can use the quantum-resistant private key to decapsulate the encapsulated session key to obtain the session key corresponding to the participant, thus completing the establishment of the quantum-resistant encrypted channel between the participant and the coordinator. The encrypted data is encrypted through the quantum-resistant encryption channel to obtain a first ciphertext, which is then sent to the coordinator. The coordinator then uses the session key corresponding to the participant to decrypt the first ciphertext to obtain the encrypted data. The coordinator analyzes and processes the encrypted data of multiple participants, and encrypts the resulting second ciphertext through the quantum-resistant encryption channel and sends it to each participant. The system receives the encrypted second ciphertext sent by the coordinator, decrypts the encrypted second ciphertext based on the session key to obtain the second ciphertext, performs decryption processing on the second ciphertext, and performs business processing based on the obtained data.

6. The method according to claim 5, characterized in that, The step of encrypting the encrypted data through the quantum-resistant encryption channel to obtain a first ciphertext and sending the first ciphertext to the coordinator includes: The session key and the encrypted data are input into the message authentication code algorithm to generate an authentication code. The authentication code is used by the coordinator to authenticate the identity of the participants and to verify the integrity of the encrypted data. The encrypted data and the authentication code are encrypted through the quantum-resistant encryption channel to obtain the first ciphertext, which is then sent to the coordinator. The coordinator generates a verification code based on the session key corresponding to the participant and the encrypted data, and verifies the consistency between the verification code and the authentication code.

7. The method according to claim 5, characterized in that, The participants are multiple, and before encrypting the encrypted data through the quantum-resistant encryption channel to obtain the first ciphertext and sending the first ciphertext to the coordinator, the method further includes: The original data is homomorphically encrypted to obtain encrypted data, wherein the original data is the model parameter variables obtained by the participants after training the initial model; After receiving the encrypted second ciphertext sent by the coordinator, and decrypting the encrypted second ciphertext based on the session key to obtain the second ciphertext, the method further includes: The second ciphertext is homomorphically decrypted to obtain the first model parameter variables that are jointly trained by the multiple participating parties. The model parameters of the initial model after training are updated using the first model parameter variables. If the initial model does not converge, the initial model is iteratively trained through the quantum-resistant encryption channel and multiple participating parties until the model converges.

8. The method according to any one of claims 5-7, characterized in that, The method further includes: Obtain the operation log, which includes: timestamp, public key digest, private key digest, and operation digest; The operation log is written to the blockchain, and the log modification permission is restricted through smart contract rules. The operation logs on the blockchain are verified for compliance based on a preset period, and the compliance verification results are sent to the audit system.

9. An encrypted communication device, characterized in that, Applied to the coordinating party, the device includes: The first generation module is used to generate quantum-resistant key pairs based on lattice cryptography algorithms, wherein the quantum-resistant key pairs include a quantum-resistant public key and a quantum-resistant private key; The first sending module is used to send the quantum-resistant public key to each participating party, so that each participating party can encapsulate the session key based on the quantum-resistant public key; The first receiving module is used to receive the encapsulated session key sent by each of the participating parties; The decapsulation module is used to decapsulate the encapsulated session key using the quantum-resistant private key to obtain the session key corresponding to each participant, and to complete the establishment of a quantum-resistant encryption channel between the coordinator and each participant, so that when the participant transmits encrypted data through the quantum-resistant encryption channel, the encrypted data is encrypted through the quantum-resistant encryption channel to obtain the first ciphertext; The first receiving module is further configured to receive the first ciphertext sent by the participating party through the quantum-resistant encryption channel; The first decryption module is used to decrypt the first ciphertext using the session key corresponding to the participant to obtain the encrypted data of the participant. The processing module is used to analyze and process the encrypted data to obtain the second ciphertext; The first sending module is further configured to send the second ciphertext to each participant through the quantum-resistant encryption channel, and each participant decrypts the second ciphertext and performs business processing based on the obtained data.

10. An encrypted communication device, characterized in that, Applied to participating parties, the device includes: The second receiving module is used to receive the quantum-resistant public key sent by the coordinator, which generates a quantum-resistant key pair based on a lattice cryptography algorithm. The quantum-resistant key pair includes a quantum-resistant public key and a quantum-resistant private key. The second generation module is used to generate a session key and encapsulate the session key based on the quantum-resistant public key; The second sending module is used to send the encapsulated session key to the coordinator, so that the coordinator can use the quantum-resistant private key to decapsulate the encapsulated session key to obtain the session key corresponding to the participant, thereby completing the establishment of the quantum-resistant encrypted channel between the participant and the coordinator. The second encryption module is used to encrypt the encrypted data through the quantum-resistant encryption channel to obtain the first ciphertext; The second sending module is further configured to send the first ciphertext to the coordinator, so that the coordinator can decrypt the first ciphertext using the session key corresponding to the participant to obtain the encrypted data, and analyze and process the encrypted data of multiple participants, encrypt the obtained second ciphertext through the quantum-resistant encryption channel and send it to each participant; The second sending module is also used to receive the encrypted second ciphertext sent by the coordinator; The second decryption module is used to decrypt the encrypted second ciphertext based on the session key to obtain the second ciphertext, and to perform decryption processing on the second ciphertext and perform business processing based on the obtained data.

11. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1 to 8.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1 to 8.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 8.

Images