Park face recognition security system based on block chain

Abstract

The invention is suitable for the technical field of artificial intelligence, and provides a block chain-based park face recognition security system, which comprises a data processor used for obtaining ciphertexts of face features of all employees of a corresponding enterprise, and uploading the ciphertexts to an enterprise block chain of the corresponding enterprise; the block chain module is used for synchronizing the ciphertext in each enterprise block chain to other enterprise block chains through a consensus mechanism, and synchronizing the ciphertext in each enterprise block chain to the park block chain of the park through a smart contract; and the block chain module is also used for comparing the hash value of the park block chain with the hash value of each enterprise block chain through the smart contract, and if the hash value of the park block chain is inconsistent with the hash value of any enterprise block chain, determining a main chain used as a data synchronization standard, and synchronizing the ciphertext stored in the main chain to other chains. The access system can be prevented from being paralyzed when the park access system is successfully attacked, and the personal data security of employees is effectively protected.

Description

Technical Field

[0001] The present application belongs to the field of artificial intelligence technology, and in particular, relates to a blockchain-based campus face recognition security system. Background Art

[0002] In the digital age, cyber attacks have become a global problem. Their frequency and complexity are constantly increasing, which not only threatens the security management of enterprises, but also may cause a large loss of business and even face huge penalties. In recent years, with the rapid development of Internet technology, the means of cyber attacks have also been evolving. These attacks not only destroy the integrity and availability of data, but also may lead to the leakage of sensitive information. Therefore, developing effective defense mechanisms to protect the security of the network environment has become an important topic in the field of information technology. At the same time, with the popularization of laws such as the "Cybersecurity Law", "Data Security Law" and "Personal Information Protection Law", employees' awareness of personal information protection has increased. In the context of frequent data leakage incidents, employees are paying more and more attention to the security of their personal information. Enterprises bear great responsibilities in maintaining the information security of employees, but also face huge challenges.

[0003] At present, face recognition technology is widely used in various occasions, from social media to security monitoring systems. Face recognition has become very popular. As personal sensitive information, the leakage of face information may lead to a series of serious consequences such as identity fraud and property loss. In large parks that use face recognition access, there are often many independent enterprises. In order to protect personal information security and prevent privacy leakage, enterprise employees may only want to enter their face information into the employing enterprise, and are unwilling to disclose it directly to the park manager. At the same time, each enterprise usually has a security department responsible for the personal information security of the enterprise and employees. However, in large parks, as property and security service roles, the park is relatively weak in network security and data security protection. Compared with enterprises in the park with independent security departments, attackers may more easily target the park. Once an attacker successfully attacks the park access system, not only will a large amount of data be lost, causing the park access system to be paralyzed, but a large amount of enterprise employee data may even be leaked, causing serious consequences.

[0004] In summary, the current campus access system faces problems such as paralysis and personal data leakage when it is successfully attacked. Summary of the invention

[0005] The embodiment of the present application provides a blockchain-based campus face recognition security system, which can solve the problem of access system paralysis and personal data leakage when the campus access system is successfully attacked.

[0006] The embodiment of the present application provides a blockchain-based campus face recognition security system, including:

[0007] Multiple data processors corresponding to multiple enterprises in the park, the data processors are used to obtain the ciphertext of facial features of all employees of the enterprise corresponding to the data processor, and upload the ciphertext to the enterprise blockchain of the corresponding enterprise;

[0008] The blockchain module is used to synchronize the ciphertext in each enterprise blockchain to other enterprise blockchains through a consensus mechanism, and synchronize the ciphertext in each enterprise blockchain to the park blockchain of the park through a smart contract, so that the ciphertext of the facial features of the employees of all enterprises are stored in the enterprise blockchains and park blockchains of all enterprises; all enterprise blockchains and park blockchains are in the same alliance chain network;

[0009] The blockchain module is also used to compare the hash value of the park blockchain with the hash value of each enterprise blockchain through a smart contract. If the hash value of the park blockchain is inconsistent with the hash value of any enterprise blockchain, the main chain used as the data synchronization standard is determined from the park blockchain and all enterprise blockchains, and the ciphertext stored in the main chain is synchronized to the park blockchain and all enterprise blockchains except the main chain.

[0010] Optionally, the data processor is specifically used to: obtain facial features of all employees of the enterprise corresponding to the data processor, and encrypt each facial feature using a homomorphic encryption public key to obtain ciphertexts of the facial features of all employees;

[0011] Homomorphic encryption public keys are configured by trusted authorities.

[0012] Optionally, the data processor is further used to store the ciphertext in a local database of the corresponding enterprise.

[0013] Optionally, a main chain used as a data synchronization standard is determined from the park blockchain and all enterprise blockchains, including:

[0014] The hash values ​​of the park blockchain and the hash values ​​of all enterprise blockchains are counted, and the enterprise blockchain corresponding to the largest number of hash values ​​is used as the main chain.

[0015] Optionally, the ciphertext stored in the main chain is synchronized to the park blockchain and all enterprise blockchains except the main chain, including:

[0016] The threshold private key shares are obtained from the local database of each enterprise through smart contracts, and all the obtained threshold private key shares are spliced ​​into a threshold private key; the threshold private key and the threshold public key are a set of threshold key pairs. The threshold public key is used to encrypt each enterprise blockchain, and the threshold private key shares are configured by a trusted institution;

[0017] The main chain is decrypted using the threshold private key through the smart contract to obtain the ciphertext stored in the main chain;

[0018] The ciphertext stored in the main chain is synchronized to the park blockchain and all enterprise blockchains except the main chain through smart contracts.

[0019] Optionally, the blockchain module is also used to encrypt each enterprise blockchain using a threshold public key after synchronizing the ciphertext stored in the main chain to the park blockchain and all enterprise blockchains other than the main chain.

[0020] Optionally, the campus face recognition security system also includes:

[0021] The park identification processor is used to obtain the facial features of people entering the park, and encrypt the facial features of the people using the homomorphic encryption public key to obtain the ciphertext of the facial features of the people, and when the ciphertext of the facial features of the people exists in the ciphertext stored in the park blockchain, the park's access control system is activated.

[0022] Optionally, the campus face recognition security system also includes:

[0023] The enterprise identification processor is used to obtain the facial features of the personnel entering the enterprise corresponding to the enterprise identification processor, and encrypt the facial features of the personnel using the homomorphic encryption public key to obtain the ciphertext of the facial features of the personnel, and when the ciphertext of the facial features of the personnel exists in the ciphertext stored in the local database of the enterprise, the access control system of the enterprise is activated.

[0024] Optionally, the facial recognition model used to obtain facial features in the park identification processor is the same as the facial recognition model used to obtain facial features in the enterprise identification processor. The facial recognition model is obtained through federated learning. The central server participating in the federated learning is located on the park side, and the multiple clients participating in the federated learning are located one-to-one on the multiple enterprise sides of the park.

[0025] The above solution of the present application has the following beneficial effects:

[0026] In an embodiment of the present application, when an attacker deletes, tampers with, or performs other attacks on the data stored in the park blockchain of the park access system, the smart contract can discover that the hash value of the park blockchain is inconsistent with the hash value of the enterprise blockchain. At this time, the smart contract will execute the data synchronization process, by determining the main chain as the data synchronization standard from the park blockchain and all enterprise blockchains, and then synchronizing the data stored in the main chain to the park blockchain, to achieve automatic data recovery, avoid paralysis of the access system, and ensure that park employees can pass normally.

[0027] In addition, since the enterprise blockchain and the campus blockchain both store the ciphertext of employees' facial features, the campus access system only has the ciphertext of employees' facial features but no employees' facial information. Therefore, when the campus access system is successfully attacked, the attacker cannot obtain the employees' facial information, thereby effectively protecting the personal data security of employees.

[0028] Other beneficial effects of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A schematic diagram of the structure of a blockchain-based campus face recognition security system provided in one embodiment of the present application;

[0031] Figure 2 A flowchart of employees entering a park is provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0032] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0033] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0034] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0035] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0036] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0037] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0038] In response to the current problems of paralysis of the access system and leakage of personal data when the park access system is successfully attacked, the embodiment of the present application provides a blockchain-based park face recognition security system. When the attacker deletes or tampers with the data stored in the park blockchain of the park access system, the smart contract can find that the hash value of the park blockchain is inconsistent with the hash value of the enterprise blockchain. At this time, the smart contract will execute the data synchronization process, determine the main chain as the data synchronization standard from the park blockchain and all enterprise blockchains, and then synchronize the data stored in the main chain to the park blockchain, so as to realize automatic data recovery, avoid paralysis of the access system, and ensure that park employees can pass normally.

[0039] In addition, since the enterprise blockchain and the campus blockchain both store the ciphertext of employees' facial features, the campus access system only has the ciphertext of employees' facial features but no employees' facial information. Therefore, when the campus access system is successfully attacked, the attacker cannot obtain the employees' facial information, thereby effectively protecting the personal data security of employees.

[0040] The following is an illustrative description of the blockchain-based campus face recognition security system provided by this application in conjunction with specific embodiments.

[0041] like Figure 1 As shown, the blockchain-based park face recognition security system provided in the embodiment of the present application includes multiple data processors corresponding to multiple enterprises in the park (such as Figure 1 Data processor 1, data processor 2 to data processor n, where n is the number of enterprises in the park) and blockchain module.

[0042] The data processor may be located at the corresponding enterprise side (such as the management server of the corresponding enterprise), and the data processor is used to obtain the ciphertext of the facial features of all employees of the enterprise corresponding to the data processor, and upload the ciphertext to the enterprise blockchain of the corresponding enterprise. Figure 1 As shown, data processor 1 uploads the obtained ciphertext to the enterprise blockchain 1 of the corresponding enterprise, data processor 2 uploads the obtained ciphertext to the enterprise blockchain 2 of the corresponding enterprise, and data processor n uploads the obtained ciphertext to the enterprise blockchain n of the corresponding enterprise.

[0043] In some embodiments of the present application, the data processor is specifically used to obtain the facial features of all employees of the enterprise corresponding to the data processor, and encrypt each facial feature using a homomorphic encryption public key (the homomorphic encryption public key is configured by a trusted institution) to obtain the ciphertext of the facial features of all employees. After obtaining the ciphertext of the facial features of all employees of the corresponding enterprise, the data processor is also used to store the ciphertext in the local database of the corresponding enterprise so as to perform facial recognition on people entering the enterprise.

[0044] Specifically, the process of the data processor obtaining the ciphertext of facial features is: first collect the facial data of employees within the enterprise, then obtain the processed image through face detection, alignment, and normalization, extract features from the processed image, and obtain a feature vector (the feature vector stores key information for face comparison), and then use the homomorphic encryption public key to encrypt the feature vector to obtain the ciphertext.

[0045] The blockchain module is used to synchronize the ciphertext in each enterprise blockchain to other enterprise blockchains through a consensus mechanism (such as the PBFT consensus mechanism), and synchronize the ciphertext in each enterprise blockchain to the park blockchain of the park through a smart contract, so that the enterprise blockchains of all enterprises (i.e., all enterprises in the park) and the park blockchain store the ciphertext of the facial features of the employees of all enterprises.

[0046] Among them, all enterprise blockchains and the park blockchain are in the same alliance chain network. Specifically, the trusted CA organization (CA for short, which refers to the authority responsible for issuing and managing digital certificates) can be designated to distribute identities to the park and each enterprise in the park, set alliance chain permissions, ensure that the entire park and internal enterprises are in the same alliance chain network, and generate public and private key pairs and certificates for each participant. Specifically, the trusted organization will generate homomorphic encryption key pairs and threshold key pairs. The homomorphic encryption key pair consists of a homomorphic encryption public key and a homomorphic encryption private key. The trusted organization will distribute the homomorphic encryption public key to each participant in the alliance chain network. The park and all enterprises use the same homomorphic encryption public key to encrypt their acquired facial features. The homomorphic encryption public key is stored by the trusted organization; the threshold key pair consists of a threshold private key and a threshold public key. The trusted organization will divide the threshold private key into n (n is the number of enterprises in the park) threshold private key shares, and distribute these n threshold private key shares to n enterprises in the alliance chain network. The threshold public key is used to encrypt each enterprise blockchain.

[0047] In the process of implementing the PBFT consensus mechanism, the enterprise blockchain of each enterprise takes turns to serve as the master node, and adopts the PBFT consensus mechanism. After the five stages of request, pre-prepare, prepare, commit and reply, the encrypted feature vectors of each enterprise employee (i.e., the ciphertext of facial features) are packaged in batches into each enterprise blockchain. It should be noted that when there is a change in employees in a certain enterprise (such as adding new employees), the enterprise blockchain of the enterprise can initiate a consensus process to synchronize ciphertexts with other blockchains and the park blockchain through the consensus mechanism, so that the ciphertexts stored in the enterprise blockchains of all enterprises (i.e., all enterprises in the park) and the park blockchain are consistent.

[0048] In order to further protect data and prevent enterprises from storing easily accessible feature vectors of other enterprise employees, a threshold encryption smart contract is introduced in the PBFT consensus process. The threshold private key share and threshold public key are generated by the CA organization. After receiving their own threshold private key share, the enterprise can store it in the local database. When PBFT is executed to the commit stage, the smart contract obtains the hash value of the current state blockchain, and automatically calls the threshold public key to perform threshold encryption on each enterprise blockchain, instead of executing the reply stage to put the block information on the chain, and release all consensus messages of each enterprise in the consensus process. Before the start of the next round of PBFT consensus pre-prepare stage, the smart contract requests each enterprise's threshold private key share to decrypt each enterprise's local chain, and then executes each stage of PBFT.

[0049] The above-mentioned blockchain module is also used to compare the hash value of the park blockchain with the hash value of each enterprise blockchain through a smart contract. If the hash value of the park blockchain is inconsistent with the hash value of any enterprise blockchain, the main chain used as the data synchronization standard is determined from the park blockchain and all enterprise blockchains, and the ciphertext stored in the main chain is synchronized to other chains in the park blockchain and all enterprise blockchains except the main chain.

[0050] Among them, the hash value of the park blockchain is obtained by calculating the ciphertext stored in the park blockchain using a hash algorithm, and the hash value of the enterprise blockchain is obtained by calculating the ciphertext stored in the enterprise blockchain using a hash algorithm (it should be noted that the hash value of the enterprise blockchain is obtained by calculating the ciphertext stored in the enterprise blockchain before encrypting the data using the threshold public key after the data is synchronized during the execution of the consensus mechanism). As a preferred example, the smart contract in the embodiment of the present application can be a Heartbeat smart contract. The Heartbeat smart contract can regularly compare the hash values ​​of the current blockchains of all participants in the alliance chain. If there is any inconsistency in the data of one party, it will automatically request each enterprise to use the threshold private key share to decrypt the local blockchain (i.e., the enterprise blockchain). The smart contract will automatically update the blockchain of the party with inconsistent data to ensure the correctness of the data.

[0051] In some embodiments of the present application, the blockchain module specifically determines the main chain used as the data synchronization standard from the park blockchain and all enterprise blockchains in the following manner: the hash values ​​of the park blockchain and the hash values ​​of all enterprise blockchains are counted, and the enterprise blockchain corresponding to the largest number of hash values ​​is used as the main chain. That is, the chain with the same hash value is used as the main chain, and the blockchain data with inconsistent data is synchronized.

[0052] In some embodiments of the present application, the blockchain module specifically synchronizes the ciphertext stored in the main chain to the park blockchain and all enterprise blockchains other than the main chain in the following manner: first, the threshold private key share is obtained from the local database of each enterprise through a smart contract, and all the obtained threshold private key shares are spliced ​​into a threshold private key (the threshold private key and the threshold public key are a set of threshold key pairs, the threshold public key is used to encrypt each enterprise blockchain, and the threshold private key share is configured by a trusted organization); then the main chain is decrypted using the threshold private key through a smart contract to obtain the ciphertext stored in the main chain; finally, the ciphertext stored in the main chain is synchronized to the park blockchain and all enterprise blockchains other than the main chain (i.e., the chain whose hash value is inconsistent with the main chain and the hash value) through a smart contract.

[0053] It is understandable that in order to protect data, the blockchain module is also used to encrypt each enterprise blockchain using a threshold public key after synchronizing the ciphertext stored in the main chain to the park blockchain and all enterprise blockchains other than the main chain.

[0054] In some embodiments of the present application, the above-mentioned park face recognition security system also includes: a park recognition processor and an enterprise recognition processor. Among them, the park recognition processor can be set on the park side, used to obtain the facial features of the person entering the park, and use the homomorphic encryption public key to encrypt the facial features of the person, obtain the ciphertext of the facial features of the person, and when the ciphertext of the facial features of the person exists in the ciphertext stored in the park blockchain, the park's access control system is opened. The enterprise recognition processor can be set on the corresponding enterprise side (as a preferred example, each enterprise side can be provided with an enterprise recognition processor), used to obtain the facial features of the person entering the enterprise corresponding to the enterprise recognition processor, and use the homomorphic encryption public key to encrypt the facial features of the person, obtain the ciphertext of the facial features of the person, and when the ciphertext of the facial features of the person exists in the ciphertext stored in the local database of the enterprise, the access control system of the enterprise is opened.

[0055] Among them, the face recognition model used to obtain facial features in the park recognition processor is the same as the face recognition model used to obtain facial features in the enterprise recognition processor. The face recognition model is obtained through federated learning. The central server participating in the federated learning is located on the park side, and the multiple clients participating in the federated learning are located on the multiple enterprise sides of the park in a one-to-one correspondence. That is, the central server sends initial model parameters to each client, and each client uses the data of the corresponding enterprise (i.e., facial features and other data) for local training, and uploads the trained model parameters to the central server of the park, so that the central server completes model aggregation and obtains a global model. This process is repeated until the global model converges, and the global model at the time of convergence is used as the above-mentioned face recognition model and distributed to each client, so that the park side and each enterprise side use the same face recognition model to extract facial features from facial images. It should be noted that the above-mentioned face recognition model can specifically be a commonly used face recognition model, such as the VGGFace model.

[0056] In another embodiment of the present application, the above-mentioned face recognition model can also be a trained model and does not need to be trained using the data of the park employees.

[0057] In other embodiments of the present application, in order to facilitate employees to quickly enter the enterprise after passing through the campus access control, the enterprise's local database may also store facial images of the enterprise's employees. The enterprise recognition processor does not need to perform complex encryption operations on the facial image, and can directly compare the employee's facial image with the facial image stored in the local database. If there is a facial image in the local database that is consistent with the employee's facial image, the enterprise's access control system will be activated to facilitate the employee's quick entry into the enterprise.

[0058] like Figure 2 As shown, under the blockchain-based park face recognition security system provided in the embodiment of the present application, the overall process for employees to enter the park is as follows:

[0059] Step 21: Employees upload their personal information to the employer according to the onboarding process;

[0060] Step 22: The employing enterprise performs face detection, alignment, normalization and feature vector extraction based on the employee's face information, and then performs homomorphic encryption;

[0061] Step 23: The employing enterprise initiates a consensus process to add the encrypted facial features of the employee to the local enterprise blockchain, and participates in updating the park blockchain and other enterprise blockchains;

[0062] Step 24: When an employee passes through, he / she must first authenticate at the park’s facial recognition terminal. After the employee has performed facial recognition, the terminal identifies the facial feature vector, encrypts the feature vector using the homomorphic encryption public key, and compares it with the ciphertext in the park’s blockchain. If the comparison passes, the employee is allowed to pass.

[0063] Step 25: When an employee enters the company where he / she is employed, he / she needs to be identified at the company's face recognition terminal. The terminal identifies the facial feature vector, encrypts the feature vector using the homomorphic encryption public key, and compares it with the ciphertext in the company's local database. If the comparison passes, the employee is allowed to enter.

[0064] In summary, when an attacker deletes or tampers with the data stored in the park blockchain of the park access system, the smart contract can find that the hash value of the park blockchain is inconsistent with the hash value of the enterprise blockchain. At this time, the smart contract will execute the data synchronization process, by determining the main chain as the data synchronization standard from the park blockchain and all enterprise blockchains, and then synchronizing the data stored in the main chain to the park blockchain, to achieve automatic data recovery, avoid paralysis of the access system, and ensure that park employees can pass normally.

[0065] In addition, since the enterprise blockchain and the campus blockchain both store the ciphertext of employees' facial features, the campus access system only has the ciphertext of employees' facial features but no employees' facial information. Therefore, when the campus access system is successfully attacked, the attacker cannot obtain the employees' facial information, thereby effectively protecting the personal data security of employees.

[0066] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles described in the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A blockchain-based campus face recognition security system, characterized in that: include: A plurality of data processors corresponding to a plurality of enterprises in the park, each of which is used to obtain the ciphertext of the facial features of all employees of the enterprise corresponding to the data processor, and upload the ciphertext to the enterprise blockchain of the corresponding enterprise; The blockchain module is used to synchronize the ciphertext in each enterprise blockchain to other enterprise blockchains through a consensus mechanism, and synchronize the ciphertext in each enterprise blockchain to the park blockchain of the park through a smart contract, so that the enterprise blockchains of all enterprises and the park blockchain store the ciphertext of the facial features of the employees of all enterprises; all enterprise blockchains and the park blockchain are in the same alliance chain network; The blockchain module is also used to compare the hash value of the park blockchain with the hash value of each of the enterprise blockchains through a smart contract. If the hash value of the park blockchain is inconsistent with the hash value of any enterprise blockchain, a main chain used as a data synchronization standard is determined from the park blockchain and all enterprise blockchains, and the ciphertext stored in the main chain is synchronized to other chains in the park blockchain and all enterprise blockchains except the main chain.

2. The park face recognition security system according to claim 1, characterized in that: The data processor is specifically used to: obtain the facial features of all employees of the enterprise corresponding to the data processor, and encrypt each facial feature using a homomorphic encryption public key to obtain the ciphertext of the facial features of all employees; The homomorphic encryption public key is configured by a trusted authority.

3. The park face recognition security system according to claim 1, characterized in that: The data processor is further used to store the ciphertext in a local database of the corresponding enterprise.

4. The park face recognition security system according to claim 2, characterized in that: Determining a main chain used as a data synchronization standard from the park blockchain and all enterprise blockchains includes: The hash values ​​of the park blockchain and the hash values ​​of all enterprise blockchains are counted, and the enterprise blockchain corresponding to the largest number of hash values ​​is used as the main chain.

5. The park face recognition security system according to claim 4, characterized in that: The synchronizing of the ciphertext stored in the main chain to the park blockchain and all enterprise blockchains other than the main chain includes: Obtaining threshold private key shares from the local database of each enterprise through a smart contract, and splicing all the acquired threshold private key shares into a threshold private key; the threshold private key and the threshold public key are a set of threshold key pairs, the threshold public key is used to encrypt each enterprise blockchain, and the threshold private key shares are configured by a trusted institution; Decrypting the main chain using the threshold private key through a smart contract to obtain the ciphertext stored in the main chain; The ciphertext stored in the main chain is synchronized to the park blockchain and all enterprise blockchains except the main chain through smart contracts.

6. The park face recognition security system according to claim 5, characterized in that: The blockchain module is also used to encrypt each of the enterprise blockchains using the threshold public key after synchronizing the ciphertext stored in the main chain to the park blockchain and all enterprise blockchains other than the main chain.

7. The park face recognition security system according to claim 2, characterized in that: The park face recognition security system also includes: The park identification processor is used to obtain the facial features of the person entering the park, and encrypt the facial features of the person using the homomorphic encryption public key to obtain the ciphertext of the facial features of the person, and when the ciphertext of the facial features of the person exists in the ciphertext stored in the park blockchain, the access control system of the park is activated.

8. The park face recognition security system according to claim 7, characterized in that: The park face recognition security system also includes: An enterprise identification processor is used to obtain the facial features of personnel entering the enterprise corresponding to the enterprise identification processor, and encrypt the facial features of the personnel using a homomorphic encryption public key to obtain the ciphertext of the facial features of the personnel, and when the ciphertext of the facial features of the personnel exists in the ciphertext stored in the local database of the enterprise, the access control system of the enterprise is activated.

9. The park face recognition security system according to claim 8, characterized in that: The facial recognition model used to obtain facial features in the park identification processor is the same as the facial recognition model used to obtain facial features in the enterprise identification processor. The facial recognition model is obtained through federated learning. The central server participating in the federated learning is located on the park side, and the multiple clients participating in the federated learning are located one by one on the multiple enterprise sides of the park.

Images