CN116028257A - Abnormal data detection method, device, electronic equipment and computer storage medium - Google Patents

Abstract

The application discloses an abnormal data detection method, an abnormal data detection device, electronic equipment and a computer storage medium, wherein the abnormal data detection method comprises the following steps: acquiring a plurality of first target data, wherein each first target data comprises at least one meta-feature, and the meta-feature is used for representing one standard of the first target data; encrypting meta-features in each first target data to obtain a disturbance value; the disturbance value is sent to the initiator to cause the initiator to detect anomalous data in the participant from the disturbance value. According to the embodiment of the application, the abnormal data can not be leaked, and the safety of the abnormal data in the detection process can be improved.

Description

Abnormal data detection method, device, electronic equipment and computer storage medium

Technical Field

The application belongs to the technical field of cloud computing, and particularly relates to an abnormal data detection method, an abnormal data detection device, electronic equipment and a computer storage medium.

Background

Under the background of big data age, federal learning is a distributed machine learning technology, so that all the sponsors and the participants do not need to exchange original data, and training of a global model under virtual fusion data is completed by exchanging a small amount of calculation results only under the condition of whole-course encryption.

The effectiveness of global model training depends largely on the validity of the raw data and whether reasonable processing is performed at the data processing stage, one of the key links being the detection and processing of anomalous data.

However, in federal learning, since the original data of each initiator and each participant are respectively stored in their local ends, and the data of each initiator and each participant cannot be accessed to each other, the initiator cannot directly detect abnormal data of other participants, and generally encrypts and transmits the data, but the data content and the data attribute are involved, and there is a risk of data leakage, so that the security of the data cannot be ensured in the process of detecting abnormal data.

Disclosure of Invention

The embodiment of the application provides an abnormal data detection method, an abnormal data detection device, electronic equipment and a computer storage medium, which can not leak abnormal data and improve the safety of the abnormal data in the detection process.

In a first aspect, an embodiment of the present application provides an abnormal data detection method, applied to a participant, where the method includes:

acquiring a plurality of first target data, wherein each first target data comprises at least one meta-feature, and the meta-feature is used for representing one standard of the first target data;

encrypting meta-features in each first target data to obtain a disturbance value;

the disturbance value is sent to the initiator to cause the initiator to detect anomalous data in the participant from the disturbance value.

In a second aspect, an embodiment of the present application provides an abnormal data detection method, applied to an initiator, where the method includes:

receiving first encrypted data and a disturbance value;

decrypting the first encrypted data by using a decryption private key to obtain third target data, wherein the third target data comprises a plurality of privacy data corresponding to meta-characteristics in the first target data;

based on the disturbance value, obtaining a public key of the participant, and decrypting the second encryption value by the public key to obtain a third encryption value;

decrypting the second encrypted data according to the third encrypted value to obtain a second feature matrix, wherein the second feature matrix comprises a plurality of meta features in a plurality of first target data;

and summing the plurality of meta-features in the second feature matrix to determine a fourth encryption value.

In a third aspect, an embodiment of the present application provides an abnormal data detection apparatus, applied to a participant, including:

the first acquisition module is used for acquiring a plurality of first target data, wherein each first target data comprises at least one meta-feature, and the meta-feature is used for representing one standard of the first target data;

the encryption module is used for encrypting the meta-feature in each first target data to obtain a disturbance value;

and the sending module is used for sending the disturbance value to the initiator so that the initiator detects abnormal data in the participant according to the disturbance value.

In a fourth aspect, an embodiment of the present application provides an abnormal data detection apparatus, applied to an initiator, including:

the receiving module is used for receiving the first encrypted data and the disturbance value;

the first decryption module decrypts the first encrypted data by using a decryption private key to obtain third target data, wherein the third target data comprises a plurality of privacy data corresponding to meta-characteristics in the first target data;

the second acquisition module acquires a public key of the participant based on the disturbance value, and decrypts the second encrypted value by the public key to obtain a third encrypted value;

the second decryption module decrypts the second encrypted data according to the third encrypted value to obtain a second feature matrix, and the second feature matrix comprises a plurality of meta features in a plurality of first target data;

and the determining module is used for summing the plurality of meta-features in the second feature matrix and determining a fourth encryption value.

In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory storing computer program instructions;

the processor, when executing the computer program instructions, implements the method as described in the first or second aspect.

In a sixth aspect, embodiments of the present application provide a computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement a method according to the first or second aspect.

According to the abnormal data detection method, device, electronic equipment and computer storage medium, through the acquisition of the plurality of first target data and the encryption processing of the meta-feature in the first target data, the meta-feature is used for representing one standard of the first target data, a disturbance value is obtained after the encryption processing, the disturbance value can ensure the safety of the data of the participator, the disturbance value is sent to the initiator, the initiator detects the abnormal data in the participator according to the disturbance value, in this way, the disturbance value only represents the situation of the first target data of the participator and the data content and the data attribute of the first target data are not involved, therefore, the initiator can acquire the standard situation of the first target data of the participator, the abnormal data detection is carried out on the first target data in the participator according to the disturbance value, and besides, the encryption processing is carried out, not only the safety of the abnormal data in the detection process is ensured, but also the safety of the abnormal data is ensured.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.

Fig. 1 is a schematic flow chart of an abnormal data detection method according to an embodiment of the first aspect of the present application;

FIG. 2 is a schematic flow chart of an abnormal data detection method according to an embodiment of a second aspect of the present application;

fig. 3 is a schematic structural diagram of an abnormal data detecting apparatus according to an embodiment of the first aspect of the present application;

fig. 4 is a schematic structural diagram of an abnormal data detecting apparatus according to an embodiment of the second aspect of the present application;

fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application are described in detail below to make the objects, technical solutions and advantages of the present application more apparent, and to further describe the present application in conjunction with the accompanying drawings and the detailed embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative of the application and are not intended to be limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present application by showing examples of the present application.

It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

As described in the background art, the inventors found that, in federal learning, since the original data of each initiator and each participant are stored in their own local terminals, and the data of each initiator and each participant cannot be accessed to each other, the initiator cannot directly detect abnormal data of other participants, and generally encrypts and transmits the data, but the data content and the data attribute are involved, and there is a risk of leaking the data, so that the security of the data cannot be ensured in the process of detecting the abnormal data.

In order to solve the problems in the prior art, the embodiment of the application provides an abnormal data detection method, an abnormal data detection device, electronic equipment and a computer storage medium. The method for detecting abnormal data provided by the embodiment of the application is described in detail below by means of specific embodiments and application scenarios thereof with reference to the accompanying drawings.

Fig. 1 is a flowchart of an abnormal data detection method provided in an embodiment of the first aspect of the present application, as shown in fig. 1, the abnormal data detection method provided in the embodiment of the present application may include steps S110 to S130, where:

s110, acquiring a plurality of first target data, wherein each first target data comprises at least one meta-feature, and the meta-feature is used for representing one standard of the first target data;

s120, encrypting meta-features in each first target data to obtain a disturbance value;

s130, sending the disturbance value to the initiator so that the initiator detects abnormal data in the participant according to the disturbance value.

Therefore, the metadata in the first target data are obtained and encrypted, wherein the metadata is used for representing one standard of the first target data, a disturbance value is obtained after encryption, the disturbance value can ensure the safety of the data of the participants, the disturbance value is sent to the initiator, and the initiator detects the abnormal data in the participants according to the disturbance value, so that the disturbance value only represents the condition of the first target data of the participants and does not relate to the data content and the data attribute of the first target data, the initiator can acquire the standard condition of the first target data of the participants, the abnormal data detection is carried out on the first target data of the participants according to the disturbance value, and the encryption ensures that the abnormal data are not leaked and the safety of the abnormal data in the detection process.

A specific implementation of each of the above steps is described below.

In one embodiment of the present application, in S110, the first target data is standard data of the participant.

Illustratively, taking any party i as an example, the meta-feature a in each first target data _j ⁽ⁱ⁾ For example, data non-null or data character type, etc., where i and j are positive integers. One meta-feature may represent a criterion of the belonging first target data, and a plurality of meta-features represent a plurality of criteria of the belonging first target data, each first target data comprising at least one meta-feature.

In one embodiment of the present application, after S110, the following steps are further included:

step 1, acquiring a plurality of second target data, wherein one second target data corresponds to privacy data of meta-features in one first target data;

illustratively, the second target data is private data stored internally by the participant, and the private data is data for federal learning, and the plurality of second target data is in one-to-one correspondence with the plurality of meta-features in the first target data.

Step 2, encrypting a plurality of second target data as a whole to obtain encrypted first encrypted data;

illustratively, a plurality of second target data are acquired

Previously, target data ∈>

Calculating the average value of all target data

Wherein U is the total number of the target data, U is the target data identifier, i is a positive integer, and the standard deviation of the target data is calculated according to the average value of the target data

Calculating to obtain second target data according to the mean value and standard deviation of the target data

And further, the second target data is encrypted as a whole.

The method specifically comprises the following steps:

generating two prime numbers and an index according to the acquired second target data;

encrypting the plurality of second target data based on the two prime numbers and one exponent by the following expression to obtain encrypted first encrypted data;

wherein y' is the first encrypted data and y is the second targetData, Q ₁ And Q ₂ And x and z are any random integer.

Illustratively, as described above, encrypting the second target data requires generating two large prime numbers Q ₁ And Q ₂ Wherein Q is ₁ ×Q ₂ Sum (Q) ₁ -1)×(Q ₂ -1) the greatest common divisor between 1). Determining a random integer x based on the second target data to obtain

Wherein k is (Q) ₁ -1) and (Q) ₂ -1) least common multiple between them, mod being the remainder function. The second target data is marked as y, and the encrypted first encrypted data is

Wherein z is any random integer.

And step 3, the first encrypted data is sent to the initiator.

In the foregoing, the first encrypted data obtained by the operation is sent to the initiator by the participant, the data sent by the participant is encrypted data, and in the process of data communication, even if the third party illegally intercepts the first encrypted data, the second target data cannot be obtained by cracking, so that the privacy security of the second target data can be ensured.

In one embodiment of the present application, in S120, encrypting meta-features in each first target data to obtain a disturbance value includes the following four steps:

the first step: according to the acquisition sequence of each first target data in the plurality of first target data, arranging the meta-features of each first target data to form a first feature matrix;

and a second step of: encrypting the first feature matrix by using a first encryption value to obtain encrypted second encryption data, wherein the first encryption value is obtained by summing up meta features in a plurality of first target data;

and a third step of: encrypting the first encryption value by using a private key of the participant to obtain an encrypted second encryption value;

fourth step: and adding the second encrypted data and the second encrypted value to obtain a disturbance value.

Taking any party i as an example, at least one meta-feature in the first target data acquired by the party i is arranged according to the acquisition order of the first target data to form a first feature matrix

Party i determines a first encryption value r

Where n is the total number of elements of the first feature matrix a.

And encrypting the first feature matrix A according to the first encryption value r to obtain encrypted second encrypted data. The party i encrypts the first encryption value through the private key of the party i to obtain an encrypted second encryption value, sums the second encryption data and the second encryption value, and combines the second encryption data and the second encryption value to obtain a disturbance value.

In one embodiment of the present application, in S130, after obtaining the disturbance value, as described above, the participant i broadcasts the disturbance value, so that the initiator knows the disturbance value, and the initiator may perform abnormal data detection on the second target data of the participant i according to the transmitted disturbance value before performing federal learning.

Fig. 2 is a flowchart of an abnormal data detection method according to an embodiment of the second aspect of the present application. The abnormal data detection method may be applied to an initiator.

As shown in fig. 2, the abnormal data detection method specifically may include steps S210 to S250, in which:

s210, receiving first encrypted data and a disturbance value;

s220, decrypting the first encrypted data by using a decryption private key to obtain third target data, wherein the third target data comprises a plurality of privacy data corresponding to meta-characteristics in the first target data;

s230, based on the disturbance value, obtaining a public key of the participant, and decrypting the second encryption value by the public key to obtain a third encryption value;

s240, decrypting the second encrypted data according to the third encrypted value to obtain a second feature matrix, wherein the second feature matrix comprises a plurality of meta features in a plurality of first target data;

s250, summing the plurality of element features in the second feature matrix to determine a fourth encryption value.

Therefore, the second encrypted value is decrypted according to the received disturbance value, the decrypted encrypted value, namely a third encrypted value, the second encrypted data is decrypted by the third encrypted value, the decrypted feature matrix, namely a second feature matrix, is obtained, summation processing is carried out on a plurality of element features in the second feature matrix again, a fourth encrypted value is obtained, whether the second feature matrix is accurate is judged according to whether the third encrypted value is identical with the fourth encrypted value, and therefore the correctness of the second feature matrix can be verified through encryption after decryption.

In one embodiment of the present application, in S210, first encrypted data and a perturbation value sent by party i are received.

In one embodiment of the present application, in S220, the initiator i decrypts the received first encrypted data, where the decrypted third target data is

The third target data comprises a plurality of privacy data corresponding to meta-characteristics in the first target data.

In one embodiment of the present application, in S230, a public key of the participant is obtained, and the second encrypted value in the disturbance value is decrypted by the public key, so as to obtain a third encrypted value r″.

In one embodiment of the present application, in S240, the second encrypted data in the disturbance value is decrypted according to the third encrypted value r″ to obtain a second feature matrix a' = { a _j ' wherein the second feature matrix comprises a plurality of meta-features in the plurality of first target data.

In one embodiment of the present application, in S250, according to the obtained second feature matrix a' = { a _j ' determining a fourth encryption value

Where n 'is the total number of elements of the feature matrix A'.

The method further comprises the following steps:

and if the decrypted third encrypted value is different from the fourth encrypted value, acquiring the disturbance value again.

For example, if the decrypted third encrypted value is different from the fourth encrypted value, that is, r '++r″, it is indicated that the obtained second feature matrix a' is inaccurate, the disturbance value is re-acquired until the accurate second feature matrix is acquired, and then whether the third target data is abnormal or not is detected through the accurate second feature matrix.

In one embodiment of the present application, in order to detect whether the third target data has an anomaly, the method may further include:

if the decrypted third encryption value is the same as the fourth encryption value, detecting whether a plurality of private data in the decrypted third target data corresponds to a plurality of meta-features in the second feature matrix one by one;

and deleting the abnormal data in the third target data under the condition that the plurality of privacy data in the decrypted third target data and the plurality of meta-features in the second feature matrix are not in one-to-one correspondence.

For example, if the decrypted third encrypted value is the same as the fourth encrypted value, i.e., r '=r ", it is indicated that the obtained feature matrix a' is accurate, i.e., a '=a, whether the third target data has abnormal data is detected through a', and if it is detected that the plurality of privacy data in the decrypted third target data corresponds to the plurality of meta-features in the second feature matrix one by one, the third target data is normal; and if the fact that the plurality of privacy data in the decrypted third target data do not correspond to the plurality of meta-features in the second feature matrix one by one is detected, the fact that the third target data are abnormal is indicated, and abnormal data in the third target data are deleted.

Through the embodiment, the initiator can detect abnormal data of the participant, so that a data base is provided for further data processing, the safety of the data is ensured, and the federal learning effect is also ensured.

It should be noted that, the application scenario described in the foregoing embodiments of the present application is for more clearly describing the technical solution of the embodiments of the present application, and does not constitute a limitation on the technical solution provided in the embodiments of the present application, and as a person of ordinary skill in the art can know, with the appearance of a new application scenario, the technical solution provided in the embodiments of the present application is also applicable to similar technical problems.

Based on the same inventive concept, the application also provides an abnormal data detection device. This is described in detail with reference to fig. 3.

Fig. 3 is a schematic structural diagram of an abnormal data detecting apparatus according to an embodiment of the first aspect of the present application. The abnormal data detection apparatus may be applied to a participant.

As shown in fig. 3, the abnormal data detecting apparatus 300 includes:

a first obtaining module 301, configured to obtain a plurality of first target data, where each first target data includes at least one meta-feature, and the meta-feature is used to represent a criterion of the first target data to which the first target data belongs;

the encryption module 302 is configured to encrypt meta features in each first target data to obtain a disturbance value;

and a sending module 303, configured to send the disturbance value to the initiator, so that the initiator detects abnormal data in the participant according to the disturbance value.

The abnormal data detecting apparatus 300 will be described in detail, specifically as follows:

in an embodiment of the present application, the abnormal data detecting apparatus 300 may further include:

the second acquisition module is used for acquiring a plurality of second target data, wherein one second target data corresponds to privacy data of meta-characteristics in one first target data;

the obtaining module is used for encrypting the plurality of second target data as a whole to obtain encrypted first encrypted data;

a sending module 303, configured to send the first encrypted data to the initiator.

In one embodiment of the present application, the encryption module 302 may specifically include:

the arrangement sub-module is used for arranging the meta-characteristics of each first target data according to the acquisition sequence of each first target data in the plurality of first target data to form a first characteristic matrix;

the first encryption sub-module is used for encrypting the first feature matrix by using a first encryption value to obtain encrypted second encrypted data, and the first encryption value is obtained by summing up meta features in a plurality of first target data;

the second encryption sub-module is used for encrypting the first encryption value by utilizing the private key of the participant to obtain an encrypted second encryption value;

the first obtaining sub-module is used for adding and processing the second encrypted data and the second encrypted value to obtain a disturbance value.

In an embodiment of the present application, the obtaining module specifically includes:

the generation sub-module is used for generating two prime numbers and one index according to the acquired second target data;

a second obtaining sub-module for encrypting the plurality of second target data based on the two prime numbers and one exponent by the following expression to obtain encrypted first encrypted data;

y' is first encrypted data, y is second target data, Q ₁ And Q ₂ And x and z are any random integer.

Fig. 4 is a schematic structural diagram of an abnormal data detecting apparatus according to an embodiment of the second aspect of the present application. The abnormal data detecting apparatus may be applied to an initiator.

As shown in fig. 4, the abnormal data detecting apparatus 300 includes:

a receiving module 401, configured to receive the first encrypted data and the disturbance value;

the first decryption module 402 decrypts the first encrypted data by using a decryption private key to obtain third target data, where the third target data includes a plurality of private data corresponding to meta features in the plurality of first target data;

the third obtaining module 403 obtains a public key of the participant based on the disturbance value, and decrypts the second encrypted value by the public key to obtain a third encrypted value;

the second decryption module 404 decrypts the second encrypted data according to the third encrypted value to obtain a second feature matrix, where the second feature matrix includes a plurality of meta features in the plurality of first target data;

the determining module 405 sums the plurality of meta-features in the second feature matrix to determine a fourth encrypted value.

In an embodiment of the present application, the abnormal data detecting apparatus 300 may further include:

and the fourth acquisition module is used for acquiring the disturbance value again if the decrypted third encryption value is different from the fourth encryption value.

In an embodiment of the present application, the abnormal data detecting apparatus 300 may further include:

the detection module is used for detecting whether the plurality of privacy data in the decrypted third target data corresponds to the plurality of meta-features in the second feature matrix one by one if the decrypted third encryption value is the same as the fourth encryption value;

and the deleting module is used for deleting the abnormal data in the third target data under the condition that the plurality of privacy data in the decrypted third target data and the plurality of meta-features in the second feature matrix are not in one-to-one correspondence.

Therefore, the metadata in the first target data are obtained and encrypted, wherein the metadata is used for representing one standard of the first target data, a disturbance value is obtained after encryption, the disturbance value can ensure the safety of the data of the participants, the disturbance value is sent to the initiator, and the initiator detects the abnormal data in the participants according to the disturbance value, so that the disturbance value only represents the condition of the first target data of the participants and does not relate to the data content and the data attribute of the first target data, the initiator can acquire the standard condition of the first target data of the participants, the abnormal data detection is carried out on the first target data of the participants according to the disturbance value, and the encryption ensures that the abnormal data are not leaked and the safety of the abnormal data in the detection process.

Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

A processor 501 and a memory 502 storing computer program instructions may be included in an electronic device.

In particular, the processor 501 may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.

Memory 502 may include mass storage for data or instructions. By way of example, and not limitation, memory 502 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. Memory 502 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 502 is a non-volatile solid state memory.

The memory may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory comprises one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described with reference to the methods according to the first or second aspects of the disclosure.

The processor 501 implements any one of the abnormal data detection methods of the above embodiments by reading and executing computer program instructions stored in the memory 502.

In one example, the electronic device may also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected to each other by a bus 510 and perform communication with each other.

The communication interface 503 is mainly used to implement communication between each module, apparatus, unit and/or device in the embodiments of the present application.

Bus 510 includes hardware, software, or both that couple the components of the abnormal data detection method or verification device to each other. By way of example, and not limitation, the buses may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a micro channel architecture (MCa) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus, or a combination of two or more of the above. Bus 510 may include one or more buses, where appropriate. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

In addition, in combination with the method for detecting abnormal data in the above embodiments, the embodiments of the present application may provide a computer storage medium for implementation. The computer storage medium has stored thereon computer program instructions; the computer program instructions, when executed by a processor, implement any of the anomaly data detection methods of the above embodiments.

It should be clear that the present application is not limited to the particular arrangements and processes described above and illustrated in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications, and additions, or change the order between steps, after appreciating the spirit of the present application.

The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be different from the order in the embodiments, or several steps may be performed simultaneously.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, which are intended to be included in the scope of the present application.

Claims (11)

1. An abnormal data detection method, for use with a participant, the method comprising:

acquiring a plurality of first target data, wherein each first target data comprises at least one meta-feature used for representing one standard of the first target data;

encrypting the meta-characteristics in each first target data to obtain a disturbance value;

and sending the disturbance value to an initiator so that the initiator detects abnormal data in the participant according to the disturbance value.

2. The method of claim 1, wherein after the acquiring the plurality of first target data, the method further comprises:

acquiring a plurality of second target data, wherein one second target data corresponds to privacy data of meta-features in one first target data;

encrypting the plurality of second target data as a whole to obtain encrypted first encrypted data;

and sending the first encrypted data to the initiator.

3. The method of claim 1, wherein encrypting the meta-feature in each of the first target data to obtain the perturbation value comprises:

according to the acquisition sequence of each first target data in the plurality of first target data, arranging the meta-features of each first target data to form a first feature matrix;

encrypting the first feature matrix by using a first encryption value to obtain encrypted second encryption data, wherein the first encryption value is obtained by summing up meta features in the plurality of first target data;

encrypting the first encryption value by using the private key of the participant to obtain an encrypted second encryption value;

and adding the second encrypted data and the second encrypted value to obtain a disturbance value.

4. The method according to claim 2, wherein encrypting the plurality of second target data as a whole to obtain encrypted first encrypted data includes:

generating two prime numbers and an index according to the acquired second target data;

encrypting the plurality of second target data based on the two prime numbers and one exponent by the following expression to obtain encrypted first encrypted data;

the y' is first encrypted data, y is second target data, Q ₁ And Q ₂ And x and z are any random integer.

5. An abnormal data detection method, applied to an initiator, comprising:

receiving the first encrypted data and the perturbation value;

decrypting the first encrypted data by using a decryption private key to obtain third target data, wherein the third target data comprises a plurality of privacy data corresponding to meta-characteristics in the plurality of first target data;

based on the disturbance value, obtaining a public key of the participant, and decrypting the second encryption value by the public key to obtain a third encryption value;

decrypting the second encrypted data according to the third encrypted value to obtain a second feature matrix, wherein the second feature matrix comprises a plurality of meta-features in the plurality of first target data;

and summing the plurality of meta-features in the second feature matrix to determine a fourth encryption value.

6. The method of claim 5, wherein the summing the plurality of meta-features in the second feature matrix is performed, and wherein after determining the fourth encrypted value, the method further comprises:

and if the decrypted third encryption value is different from the fourth encryption value, acquiring a disturbance value again.

7. The method of claim 5, wherein the method further comprises:

if the decrypted third encryption value is the same as the fourth encryption value, detecting whether a plurality of privacy data in the decrypted third target data corresponds to a plurality of meta-features in the second feature matrix one by one;

and deleting the abnormal data in the third target data under the condition that the decrypted plurality of private data in the third target data and the plurality of meta-features in the second feature matrix are not in one-to-one correspondence.

8. An abnormal data detection apparatus for use with a participant, the apparatus comprising:

a first acquisition module, configured to acquire a plurality of first target data, where each first target data includes at least one meta-feature, and the meta-feature is used to represent a criterion of the first target data to which the first target data belongs;

the encryption module is used for encrypting the meta-feature in each first target data to obtain a disturbance value;

and the sending module is used for sending the disturbance value to an initiator so that the initiator detects abnormal data in the participant according to the disturbance value.

9. An abnormal data detection apparatus for use with an initiator, the apparatus comprising:

the receiving module is used for receiving the first encrypted data and the disturbance value;

the first decryption module is used for decrypting the first encrypted data by using a decryption private key to obtain third target data, wherein the third target data comprises a plurality of privacy data corresponding to meta-characteristics in the first target data;

the second acquisition module is used for acquiring a public key of the participant based on the disturbance value, and decrypting the second encryption value by the public key to obtain a third encryption value;

the second decryption module is used for decrypting the second encrypted data according to the third encrypted value to obtain a second feature matrix, and the second feature matrix comprises a plurality of meta-features in the plurality of first target data;

and the determining module is used for summing the plurality of meta-features in the second feature matrix and determining a fourth encryption value.

10. An electronic device, the electronic device comprising: a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor performs the steps of anomaly data detection as claimed in any one of claims 1 to 4 or 5 to 7.

11. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon computer program instructions which, when executed by a processor, implement the step of abnormal data detection according to any of claims 1-4 or 5-7.

Images