Anti-malicious rapid and secure aggregation method and device

Abstract

The invention discloses an anti-malicious rapid and safe aggregation method and device, and the method comprises the steps: S1, each of a plurality of participants obtains a plurality of random numbers, and the number of the participants is the same as the number of the random numbers obtained by each participant; s2, each participant generates a corresponding number of pseudo-random numbers for the current aggregation round by using a plurality of random numbers, and calculates the generated pseudo-random numbers to obtain a pseudo-random number calculation result; s3, each participant processes the data to be aggregated according to a pseudo-random number calculation result, and all participants send a processing result to the server for aggregation calculation; and S4, each participant receives the aggregation calculation result returned by the server, and processes the aggregation calculation result to obtain an aggregated result.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for rapidly and securely aggregating data against malicious intent. Background Art

[0002] In today's era of data explosion, massive amounts of data are generated and transmitted through various heterogeneous devices and systems. These data are usually stored in different institutions, forming the so-called "data island" phenomenon. Especially in the fields of medical care, finance, government, and supply chain involving sensitive information, this data island problem is particularly prominent. Traditional centralized machine learning methods rely on a large amount of high-quality data to train models, but a single institution often finds it difficult to have enough data volume and diverse distribution characteristics to support the construction of high-quality models. To solve this problem, a feasible way is to aggregate data sets from various institutions.

[0003] In the Federated Learning (FL) framework, each participant (i.e., client) retains its local data and only uploads model parameters to the central server; the latter is responsible for aggregating all local updates and generating a global model, which is then distributed to each client for subsequent iterative optimization. However, studies have shown that even if only model parameters are transmitted, a certain degree of information leakage may still occur. For example, member reasoning attacks can infer whether a specific sample is used in the training process. In order to further strengthen the privacy protection of federated learning, researchers have proposed a variety of solutions to build privacy protection mechanisms using technologies such as differential privacy, homomorphic encryption, functional encryption, and secure aggregation.

[0004] Existing research mainly focuses on the following aspects:

[0005] Secure Multi-party Computation (SMPC) is a key technology for protecting data privacy. By allowing multiple parties to collaborate on computations without the need for a single trusted third party, the risk of data leakage is avoided. Google introduced it into federated learning in 2017 and proposed a federated learning framework based on SMPC. However, this solution still requires all clients to frequently broadcast communications, which results in high communication overhead.

[0006] Differential Privacy (DP) protects privacy by introducing noise into model updates so that the output model cannot accurately reflect the model of any single user. However, the introduction of noise will lead to a decrease in the performance of the aggregated model, and this method needs to be further optimized.

[0007] Homomorphic encryption (HE) encrypts the model gradient for data inclusion, preventing third-party servers from obtaining gradient data, thereby avoiding the server from cracking the gradient to obtain the original data information of the participants. However, due to the introduction of homomorphic computing, this scheme has a large computational overhead and requires all participants to use the same public and private key pairs for data encryption and decryption, which cannot resist the problem of collusion between the server and the participants.

[0008] In summary, although the existing technology has made some progress in cryptographic security or communication efficiency, it still has the following major shortcomings:

[0009] 1. Lack of effective protection against collusion attacks: Most existing solutions do not fully consider how to prevent potential collusion between malicious servers and some clients.

[0010] 2. High communication overhead: For example, SMPC-based technologies require frequent point-to-point communications, which increases the burden on the overall system.

[0011] 3. Loss of precision: Some strategies, such as differential privacy, blur individual contributions by introducing noise, which can improve privacy levels but also sacrifice model performance accordingly.

[0012] In view of the above technical problems, the present invention proposes a fast and secure aggregation method and device that is anti-malicious. Summary of the invention

[0013] The purpose of the present invention is to address the defects of the prior art and provide an anti-malicious fast and secure aggregation method and device, which not only solves the privacy leakage risk in the existing federated learning framework, but also greatly improves the communication efficiency and maintains the high accuracy of model training, providing strong support for large-scale data collaboration across institutions.

[0014] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0015] A fast and secure aggregation method against malicious intent, comprising:

[0016] S1. Each of the several participants obtains several random numbers, wherein the number of the participants is the same as the number of random numbers obtained by each participant;

[0017] S2. Each participant uses several random numbers to generate a corresponding number of pseudo-random numbers for the current aggregation round, and calculates the generated pseudo-random numbers to obtain pseudo-random number calculation results;

[0018] S3. Each participant processes the data to be aggregated according to the result of pseudo-random number calculation, and all participants send the processed results to the server for aggregate calculation;

[0019] S4. Each participant receives the aggregate calculation results returned by the server, and processes the aggregate calculation results to obtain the aggregated results.

[0020] Furthermore, the step S1 is specifically as follows:

[0021] S11. Each participant generates a public key and a private key based on an asymmetric encryption algorithm, and broadcasts the public key to other participants;

[0022] S12. The first participant generates multiple random numbers, concatenates and encrypts the generated random numbers, and sends the processing results to other participants;

[0023] S13. The other participants generate multiple random numbers, encrypt the generated random numbers, and send the processing results to the other participants;

[0024] S14. The other participants decrypt the encryption results of the first participant and other participants to obtain the final random numbers.

[0025] Furthermore, in step S3, each participant processes the data to be aggregated according to the pseudo-random number calculation result, including:

[0026] The first participant processes the data to be aggregated, which is expressed as:

[0027] E(D1)=D1+f1(k)+F(r 11 ,k)

[0028] Wherein, E(D1) represents the result of the first participant processing the data to be aggregated; D1 represents the data to be aggregated of the first participant; f1(k) represents the result of the pseudo-random number calculation of the first participant; F(r 11 ,k) represents the pseudo-random number of the first participant.

[0029] Furthermore, in step S3, each participant processes the data to be aggregated according to the pseudo-random number calculation result, including:

[0030] Other participants encrypt the aggregated data, which is expressed as:

[0031] E(D i )=D i +f i (k)

[0032] Among them, E(D i ) represents the result of other participants processing the aggregated data; D i Indicates the data to be aggregated from other participants; f i(k) represents the pseudo-random number calculation result of other participants; i∈2, 3,…, N; N represents the number of participants.

[0033] Furthermore, in step S3, the server performs aggregate calculation, which is expressed as:

[0034] E(D)=E(D1)+E(D2)+...+E(D N )

[0035] Where E(D) represents the aggregate calculation result of the server; E(D2) represents the result of the second participant processing the aggregated data; E(D N ) represents the result of processing the aggregated data by the Nth participant.

[0036] Furthermore, in step S4, the aggregate calculation result is processed as follows:

[0037] D=E(D)-F(r 11 ,k)

[0038] Where D represents the result of each participant processing the aggregate calculation result.

[0039] Accordingly, a fast and secure aggregation device for resisting maliciousness is also provided, which is used to execute the fast and secure aggregation method for resisting maliciousness. The aggregation device includes a processor, and the processor is provided with:

[0040] A generation module, used for each of the plurality of participants to generate N random numbers, wherein the N random numbers generated by each participant include those generated by itself and / or by other participants;

[0041] The generation module is used for each participant to use N random numbers to generate N pseudo-random numbers for the current aggregation round, and calculate f based on the N pseudo-random numbers i (k);

[0042] Aggregation module, for each participant according to f i (k) encrypting the data to be aggregated, and all participants send the encrypted results to the server for aggregate calculation;

[0043] The decryption module is used for each participant to receive the aggregate calculation results returned by the server, and to decrypt the aggregate calculation results to obtain the aggregated results.

[0044] Furthermore, the processor is connected to a memory for storing data or instructions.

[0045] Furthermore, the processor is connected to a transmission device for transmitting data with an external device.

[0046] Furthermore, the processor is connected to an input / output device for inputting or outputting information.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. Anti-collusion attack: Through the carefully designed random number blinding mechanism, unless all other participants (i.e. N-1 participants) collude with the server, it is impossible to obtain the data information of any participant. This design greatly improves the security of the system and effectively prevents internal or external malicious behavior.

[0049] 2. High efficiency and low communication overhead: The random number blinding technology is used to encrypt the gradient, avoiding the frequent interaction process in the traditional method, thereby significantly reducing the communication cost. In addition, this method has higher computing performance and can achieve faster data processing speed while maintaining security.

[0050] 3. No loss of precision: Unlike methods that introduce noise to protect privacy, this solution does not cause a decrease in the accuracy of model training during the calculation process. The accuracy of the final aggregation result is exactly the same as when the plaintext data is directly used for aggregation, ensuring the construction of a high-quality model. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 This is a flow chart of a fast and secure aggregation method against malicious intent provided in Example 1;

[0052] Figure 2 This is a structural diagram of the rapid and secure data aggregation provided in Example 1. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0054] The purpose of the present invention is to address the defects of the prior art and provide a data anonymization transmission method, system and device based on data hosting.

[0055] Embodiment 1

[0056] This embodiment provides a fast and secure aggregation method to resist malicious attacks, such as Figure 1-2 As shown, including:

[0057] S1. Each of the several participants obtains several random numbers, wherein the number of the participants is the same as the number of random numbers obtained by each participant;

[0058] S2. Each participant uses several random numbers to generate a corresponding number of pseudo-random numbers for the current aggregation round, and calculates the generated pseudo-random numbers to obtain pseudo-random number calculation results;

[0059] S3. Each participant processes the data to be aggregated according to the result of pseudo-random number calculation, and all participants send the processed results to the server for aggregate calculation;

[0060] S4. Each participant receives the aggregate calculation results returned by the server, and processes the aggregate calculation results to obtain the aggregated results.

[0061] In this embodiment, there are N participants (P1, P2, ... N ), a third-party server S.

[0062] Each participant has a piece of data D to be aggregated. i , each participant obtains the aggregated result D = D1 + D2 + ... + D N .

[0063] In step S1, each of the several participants obtains several random numbers, wherein the number of the participants is the same as the number of random numbers obtained by each participant, specifically:

[0064] S11. Each participant generates a public key and a private key based on an asymmetric encryption algorithm, and broadcasts the public key to other participants;

[0065] Each of the N participants will generate a public-private key pair (sk i ,pk i ), each participant broadcasts the public key so that other participants can obtain the public key pk i , where pk i Represents the public key, sk i Represents the private key; i represents the i-th participant, i∈1,2,…,N; N represents the number of participants.

[0066] S12. The first participant generates multiple random numbers, concatenates and encrypts the generated random numbers, and sends the processing results to other participants;

[0067] Participant P1 generates M random numbers r 11 ,r 12 ,...,r 1M , and r 11 and r 1xConcatenate to form a number R x = r 11 ||r 1x , and use pk i to encrypt R x to obtain the encrypted result E(R x ), and send the encrypted result E(R x ) to the i-th participant. Concatenation means combining two strings into one, for example, 123 and 456 are concatenated into 123||456.

[0068] Among them, P1 represents the first participant; M represents the number of random numbers, and the value of M is the same as the value of N; x represents the x-th random number, x ∈ 2,..., M; R x represents the concatenated value; E(R x ) represents the encrypted result. In this embodiment, each participant pre-knows which participant its own random number is to be sent to. Therefore, when encrypting the concatenated value using the public key, the public key of the participant after sending is used. For example, if P1 is to send the generated random number to P2, P3, and P4, then when encrypting the concatenated value in P1, the public keys of P2, P3, and P4 are used, which facilitates P2, P3, and P4 to decrypt using their own private keys in the subsequent decryption. It should be noted that the random numbers are sent backward, that is, P2, P3, and P4 can obtain the random numbers sent by P1, but P2 cannot obtain the random numbers sent by P3, and P3 cannot obtain the random numbers sent by P4.

[0069] S13. Other participants generate multiple random numbers, encrypt the generated random numbers, and send the processing results to other participants;

[0070] Participant P i generates M - i (M minus i) random numbers r iy (i < y), and uses the public key pk i to encrypt r iy to obtain the encrypted result E(r iy ), and send the encrypted result E(r iy ) to other participants P j .

[0071] In step S13, i ∈ 2, 3,..., N; y represents the y-th random number, y ∈ i + 1,..., M.

[0072] In this embodiment, each participant knows in advance which participant its random number will be sent to. Therefore, when the random number is encrypted using a public key, the public key of the participant after the transmission is used. For example, if P2 wants to send the generated random number to P3 and P4, then the public key of P3 and P4 is used to encrypt the random number in P2, so that P3 and P4 can use their own private key for decryption in the subsequent decryption. It should be noted that the random number is sent backward, that is, P3 and P4 can obtain the random number sent by P2, but P3 cannot obtain the random number sent by P4.

[0073] S14. The other participants decrypt the encryption results of the first participant and other participants to obtain the final random numbers.

[0074] Participant P j Through its own private key sk i The E(R x ) decryption to obtain r 11 ||r 1x , and split it to obtain r 11 and r 1x Then, the other participants P in step S13 i E(r iy ) to decrypt and obtain r iy (i <y)。

[0075] In step S14, the participant P j The value of j in the equation is the same as the private key sk i The value of i, E(R x ) and r 1x The value of x, E(r iy ) and r iy The value of y is the same; P j The value of j is greater than P i The value of i in .

[0076] As shown in Table 1 below, the random numbers obtained by the four participants after steps S11-S14 are illustrated as follows:

[0077] Table 1

[0078] Participants Random Numbers <![CDATA[P1]]> <![CDATA[r 11 ,r 12 ,r 13 ,r 14 ]]> <![CDATA[P2]]> <![CDATA[r 11 ,r 12 ,r 23 ,r 24 ]]> <![CDATA[P3]]> <![CDATA[r 11 ,r 13 ,r 23 ,r 34 ]]> <![CDATA[P4]]> <![CDATA[r 11 ,r 14 ,r 24 ,r 34 ]]>

[0079] In Table 1, r in participant P1 11 , r 12 , r 13 , r 14 is generated by P1 itself, and r in participant P2 23 , r 24 is generated by P2 itself; r in participant P3 34Generated by P3 itself.

[0080] In Table 1, the r of participant P2 11 , r 12 is obtained from participant P1, and r in participant P3 11 , r 13 is obtained from participant P1, and r in participant P3 23 is obtained from participant P2, and r in participant P4 11 , r 14 is obtained from participant P1, and r in participant P4 24 is obtained from participant P2, and r in participant P4 34 It is obtained from participant P3.

[0081] After the method of steps S11-S14 is executed, each participant P i ∈(P1,...,P N ) all have M random numbers.

[0082] In step S2, each participant uses several random numbers to generate a corresponding number of pseudo-random numbers for the current aggregation round, and calculates the generated pseudo-random numbers to obtain pseudo-random number calculation results.

[0083] Participant P i ∈(P1,...,P N ) Use M random numbers to perform zero secret sharing on the current aggregated round k, generating M pseudo-random numbers F(r iy , k), where y∈i+1,…,M, i∈1,2,3,…,N; and the generated pseudo-random number is calculated to obtain the pseudo-random number calculation result f i (k), denoted as f i (k) = [-F(r 1i ,k)]+...+[F(r iM ,k)], the sign before F depends on whether r is generated by itself. If it is generated by itself, it is positive, and if it is obtained from other participants, it is negative.

[0084] As shown in Table 2 below, the pseudo-random numbers of four participants are given as an example:

[0085] Table 2

[0086] Participants <![CDATA[f i (k)]]> <![CDATA[P1]]> <![CDATA[F(r 12 ,k)+F(r 13 ,k)+F(r 14 ,k)]]> <![CDATA[P2]]> <![CDATA[-F(r 12 ,k)+F(r 23 ,k)+F(r 24 ,k) <!-- 5 -->]]> <![CDATA[P3]]> <![CDATA[-F(r 13 ,k)-F(r 23 ,k)+F(r 34 ,k)]]> <![CDATA[P4]]> <![CDATA[-F(r 14 ,k)-F(r 24 ,k)-F(r 34 ,k)]]>

[0087] In step S3, each participant processes the data to be aggregated according to the pseudo-random number calculation result, and all participants send the processing results to the server for aggregation calculation.

[0088] The first participant P1 performs blind processing on the aggregated data D1, which is expressed as: E(D1) = D1 + f1(k) + F(r 11 ,k).

[0089] Other participants P i ∈(P2,...,P N ) Treat aggregate data D i Processed, expressed as, E(D i )=D i +f i (k).

[0090] All participants send the processing results to the third-party server S for aggregate calculation.

[0091] The third-party service S performs aggregate calculations, expressed as: E(D) = E(D1) + E(D2) + ... + E(D N ) and returns the result to other parties.

[0092] In step S4, each participant receives the aggregate calculation result returned by the server, and processes the aggregate calculation result to obtain an aggregated result.

[0093] Participant P i ∈(P1,...,P N ) The aggregated result E(D) is unblinded and expressed as: D = E(D) - F(r 11 ,k).

[0094] Compared with the prior art, the present invention has the following beneficial effects:

[0095] 1. Anti-collusion attack: Through the carefully designed random number blinding mechanism, unless all other participants (i.e. N-1 participants) collude with the server, it is impossible to obtain the data information of any participant. This design greatly improves the security of the system and effectively prevents internal or external malicious behavior.

[0096] 2. High efficiency and low communication overhead: The random number blinding technology is used to encrypt the gradient, avoiding the frequent interaction process in the traditional method, thereby significantly reducing the communication cost. In addition, this method has higher computing performance and can achieve faster data processing speed while maintaining security.

[0097] 3. No loss of precision: Unlike methods that introduce noise to protect privacy, this solution does not cause a decrease in the accuracy of model training during the calculation process. The accuracy of the final aggregation result is exactly the same as when the plaintext data is directly used for aggregation, ensuring the construction of a high-quality model.

[0098] Embodiment 2

[0099] This embodiment provides an anti-malicious fast and secure aggregation device, which is used to execute an anti-malicious fast and secure aggregation method of embodiment 1. The aggregation device includes a processor, and the processor is provided with:

[0100] A generation module, used for each of the multiple participants to generate N random numbers, wherein the N random numbers generated by each participant include those generated by itself and / or other participants;

[0101] The generation module is used for each participant to use N random numbers to generate N pseudo-random numbers for the current aggregation round, and calculate f based on the N pseudo-random numbers i (k);

[0102] Aggregation module, for each participant according to f i (k) encrypting the data to be aggregated, and all participants send the encrypted results to the server for aggregate calculation;

[0103] The decryption module is used for each participant to receive the aggregate calculation results returned by the server, and to decrypt the aggregate calculation results to obtain the aggregated results.

[0104] The processor described in this embodiment may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0105] The processor described in the present embodiment is connected with a memory for storing data or instructions. The memory may include a large capacity memory for data or instructions. For example, but not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory may be inside or outside the data processing device. In a specific embodiment, the memory is a non-volatile memory. In a specific embodiment, the memory includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0106] The memory can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor. The processor reads and executes the computer program instructions stored in the memory.

[0107] The processor described in this embodiment is connected to a transmission device for transmitting data with an external device. The transmission device can be used to receive or send data via a network. The above-mentioned specific examples of the network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0108] The processor in this embodiment is connected to an input / output device for inputting or outputting information. The input / output device is used to input or output information. In this embodiment, the input information is the data to be aggregated by each participant, and the output information is the result of aggregation.

[0109] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A fast and secure aggregation method against malicious intent, characterized in that: include: S1. Each of the several participants obtains several random numbers, wherein the number of the participants is the same as the number of random numbers obtained by each participant; S2. Each participant uses several random numbers to generate a corresponding number of pseudo-random numbers for the current aggregation round, and calculates the generated pseudo-random numbers to obtain pseudo-random number calculation results; S3. Each participant processes the data to be aggregated according to the result of pseudo-random number calculation, and all participants send the processed results to the server for aggregate calculation; S4. Each participant receives the aggregate calculation results returned by the server, and processes the aggregate calculation results to obtain the aggregated results.

2. The method for rapid and secure aggregation against malicious intent according to claim 1, characterized in that: The step S1 is specifically as follows: S11. Each participant generates a public key and a private key based on an asymmetric encryption algorithm, and broadcasts the public key to other participants; S12. The first participant generates multiple random numbers, concatenates and encrypts the generated random numbers, and sends the processing results to other participants; S13. The other participants generate multiple random numbers, encrypt the generated random numbers, and send the processing results to the other participants; S14. The other participants decrypt the encryption results of the first participant and other participants to obtain the final random numbers.

3. The method for fast and secure aggregation against malicious intent according to claim 2, characterized in that: In step S3, each participant processes the data to be aggregated according to the pseudo-random number calculation result, including: The first participant processes the data to be aggregated, which is expressed as: E(D1)=D1+f1(k)+F(r 11 ,k) Wherein, E(D1) represents the result of the first participant processing the data to be aggregated; D1 represents the data to be aggregated of the first participant; f1(k) represents the result of the pseudo-random number calculation of the first participant; F(r 11 ,k) represents the pseudo-random number of the first participant.

4. The method for fast and secure aggregation against malicious intent according to claim 3, characterized in that: In step S3, each participant processes the data to be aggregated according to the pseudo-random number calculation result, including: Other participants encrypt the aggregated data, which is expressed as: E(D i )=D i +f i (k) Among them, E(D i ) represents the result of other participants processing the aggregated data; D i Indicates the data to be aggregated from other participants; f i (k) represents the pseudo-random number calculation result of other participants; i∈2, 3,…, N; N represents the number of participants.

5. The method for fast and secure aggregation against malicious intent according to claim 4, characterized in that: In step S3, the server performs aggregate calculation, which is expressed as: E(D)=E(D1)+E(D2)+...+E(D N ) Where E(D) represents the aggregate calculation result of the server; E(D2) represents the result of the second participant processing the aggregated data; E(D N ) represents the result of processing the aggregated data by the Nth participant.

6. The method for fast and secure aggregation against malicious intent according to claim 5, characterized in that: In step S4, the aggregate calculation result is processed, which is expressed as: D=E(D)-F(r 11 ,k) Where D represents the result of each participant processing the aggregate calculation result.

7. An anti-malicious fast and secure aggregation device, used to execute an anti-malicious fast and secure aggregation method according to any one of claims 1 to 6, the aggregation device comprising a processor, characterized in that: The processor is provided with: A generation module, used for each of the multiple participants to generate N random numbers, wherein the N random numbers generated by each participant include those generated by itself and / or other participants; The generation module is used for each participant to use N random numbers to generate N pseudo-random numbers for the current aggregation round, and calculate f based on the N pseudo-random numbers i (k); Aggregation module, for each participant according to f i (k) encrypting the data to be aggregated, and all participants send the encrypted results to the server for aggregate calculation; The decryption module is used for each participant to receive the aggregate calculation results returned by the server, and to decrypt the aggregate calculation results to obtain the aggregated results.

8. The anti-malicious fast and secure aggregation device according to claim 7, characterized in that: The processor is connected to a memory for storing data or instructions.

9. The anti-malicious fast and secure aggregation device according to claim 7, characterized in that: The processor is connected with a transmission device for transmitting data with an external device.

10. The anti-malicious fast and secure aggregation device according to claim 7, characterized in that: The processor is connected to an input / output device for inputting or outputting information.

Images