CN117391701A - Method and device for detecting theft and brushing behaviors, computer equipment and storage medium - Google Patents

Method and device for detecting theft and brushing behaviors, computer equipment and storage medium Download PDF

Info

Publication number
CN117391701A
CN117391701A CN202311153887.3A CN202311153887A CN117391701A CN 117391701 A CN117391701 A CN 117391701A CN 202311153887 A CN202311153887 A CN 202311153887A CN 117391701 A CN117391701 A CN 117391701A
Authority
CN
China
Prior art keywords
data
theft
user
homomorphic
result
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202311153887.3A
Other languages
Chinese (zh)
Inventor
王军辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Bank of China Ltd
Original Assignee
Bank of China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Bank of China Ltd filed Critical Bank of China Ltd
Priority to CN202311153887.3A priority Critical patent/CN117391701A/en
Publication of CN117391701A publication Critical patent/CN117391701A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/008—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols involving homomorphic encryption
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/08—Key distribution or management, e.g. generation, sharing or updating, of cryptographic keys or passwords
    • H04L9/0861—Generation of secret information including derivation or calculation of cryptographic keys or passwords
    • H04L9/0869—Generation of secret information including derivation or calculation of cryptographic keys or passwords involving random numbers or seeds

Abstract

The application relates to a theft and brushing behavior detection method, a theft and brushing behavior detection device, a computer device, a storage medium and a computer program product. Relates to the field of artificial intelligence, the method comprises the following steps: when the card swiping behavior of the user is detected, personal data of the user after homomorphic encryption processing is obtained; homomorphic operation is carried out on personal data of a user through a theft and brushing behavior detection model, and homomorphic operation results are obtained; feeding back homomorphic operation results to a data provider; receiving an operation decryption result fed back by the data provider according to the homomorphic operation result; and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result. When the card swiping behavior of the user is detected, homomorphic operation is performed by acquiring homomorphic encrypted user personal data, and homomorphic operation results are submitted to the data provider for decryption, so that more comprehensive data can be introduced to detect the theft swiping behavior under the condition that user privacy data is not revealed, and accurate detection on the theft swiping behavior is realized.

Description

Method and device for detecting theft and brushing behaviors, computer equipment and storage medium
Technical Field
The present application relates to the field of computer technology, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for detecting a theft and brushing behavior.
Background
With the development of computer technology, the importance of network information security is increasing, and the network information security mainly refers to that hardware, software of a network system and data in the system are protected from being damaged, changed and leaked due to accidental or malicious reasons, the system continuously and reliably operates normally, and network service is not interrupted. At present, a hacker can steal user information in a malicious software mode and the like to endanger network information security, for example, the hacker can forge user behaviors through the stolen user information, so that a fake card is used for carrying out theft and brushing and the like, and therefore abnormal user behavior data are required to be detected, and network information security is protected.
In the prior art, an artificial intelligent machine learning method is generally used for detecting whether the user behavior data are stolen, however, if the user behavior data are detected in the method, only the client information or the transaction data of a single mechanism are used for judging the property of the transaction to be inaccurate, so that various operator data and public data are required to be introduced as data supports, the introduced data are not comprehensive enough, and the accuracy of the stolen behavior detection is affected.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a method, an apparatus, a computer device, a computer-readable storage medium, and a computer program product for detecting a theft behavior that can effectively improve the accuracy of detecting a theft behavior of a user.
In a first aspect, the present application provides a method for detecting a theft behavior. The method comprises the following steps:
when the card swiping behavior of a user is detected, acquiring user personal data of the user after homomorphic encryption processing;
homomorphic operation is carried out on the user personal data through a theft and brushing behavior detection model, so that homomorphic operation results are obtained, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
feeding back the homomorphic operation result to a data provider of the user personal data;
receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In one embodiment, the data provider for feeding back the homomorphic operation result to the user personal data includes:
determining result feedback data according to the sum of the homomorphic operation result and the random number;
Feeding back the result feedback data to a data provider of the user personal data;
the receiving the operation decryption result fed back by the data provider according to the homomorphic operation result comprises the following steps:
receiving a data decryption result fed back by the data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data;
and determining an operation decryption result based on the difference between the data decryption result and the random number.
In one embodiment, the method further includes, before performing homomorphic operation on the user personal data by using the piracy detection model to obtain a homomorphic operation result:
acquiring historical personal data of a target user after homomorphic encryption;
constructing model training data with data labels based on the historical personal data;
and training the initial theft and brushing behavior detection model based on the model training data with the data tag to obtain the theft and brushing behavior detection model.
In one embodiment, the obtaining the homomorphic encrypted historical personal data of the target user includes:
transmitting a data collaboration request of the target user to the data provider;
and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
In one embodiment, the constructing model training data with data tags based on the historical personal data includes:
acquiring target user data and card swiping historical data of a target user in the historical data;
and constructing model training data based on the target user data and the historical personal data, and adding a data tag to the model training data through the swipe card historical data to obtain model training data with the data tag.
In one embodiment, the method further comprises:
determining a theft swiping risk level of the card swiping behavior based on the theft swiping behavior detection result;
generating a risk prompt message corresponding to the theft and brushing risk level;
and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
In a second aspect, the application further provides a device for detecting the brushing behavior. The device comprises:
the data acquisition module is used for acquiring user personal data of the user after homomorphic encryption processing when detecting the card swiping behavior of the user;
the homomorphic operation module is used for carrying out homomorphic operation on the user personal data through the theft and brushing behavior detection model to obtain homomorphic operation results, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
The data feedback module is used for feeding back the homomorphic operation result to a data provider of the user personal data;
the data receiving module is used for receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and the behavior detection module is used for determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor which when executing the computer program performs the steps of:
when the card swiping behavior of a user is detected, acquiring user personal data of the user after homomorphic encryption processing;
homomorphic operation is carried out on the user personal data through a theft and brushing behavior detection model, so that homomorphic operation results are obtained, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
feeding back the homomorphic operation result to a data provider of the user personal data;
receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
And determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
when the card swiping behavior of a user is detected, acquiring user personal data of the user after homomorphic encryption processing;
homomorphic operation is carried out on the user personal data through a theft and brushing behavior detection model, so that homomorphic operation results are obtained, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
feeding back the homomorphic operation result to a data provider of the user personal data;
receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprises a computer program which, when executed by a processor, implements the steps of:
When the card swiping behavior of a user is detected, acquiring user personal data of the user after homomorphic encryption processing;
homomorphic operation is carried out on the user personal data through a theft and brushing behavior detection model, so that homomorphic operation results are obtained, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
feeding back the homomorphic operation result to a data provider of the user personal data;
receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
The method, the device, the computer equipment, the storage medium and the computer program product for detecting the swiping behavior of the user acquire personal data of the user after homomorphic encryption processing when detecting the swiping behavior of the user; homomorphic operation is carried out on personal data of a user through a theft and brushing behavior detection model, and homomorphic operation results are obtained; feeding back homomorphic operation results to a data provider of personal data of the user; receiving an operation decryption result fed back by the data provider according to the homomorphic operation result; and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result. When the card swiping behavior of the user is detected, homomorphic operation is performed by acquiring homomorphic encrypted user personal data, and homomorphic operation results are submitted to the data provider for decryption, so that more comprehensive data can be introduced to detect the theft swiping behavior under the condition that user privacy data is not revealed, and accurate detection on the theft swiping behavior is realized.
Drawings
FIG. 1 is an application environment diagram of a method for detecting theft behavior in one embodiment;
FIG. 2 is a flow chart of a method for detecting a theft behavior according to an embodiment;
FIG. 3 is a flow chart of a theft risk alert process in one embodiment;
FIG. 4 is a block diagram of a theft behavior detection device in one embodiment;
fig. 5 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The method for detecting the brushing behavior can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the detection server 104 via a network, and the detection server 104 communicates with the data provider server 106 via a network. The data storage system may store data that the detection server 104 needs to process. The data storage system may be integrated on the detection server 104 or may be located on the cloud or other network server. When the user performs the card swiping action through the terminal 102, the terminal 102 may submit the relevant action data of the current card swiping action to the detection server 104, and when the detection server 104 receives the relevant action data of the card swiping action, it is determined that the card swiping action of the user has been detected, at which time the user personal data of the user after the homomorphic encryption processing may be acquired from the data provider server 106; then homomorphic operation is carried out on the personal data of the user through a theft and brushing behavior detection model, and a homomorphic operation result is obtained, wherein the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data; then feeding back homomorphic operation results to a data provider server 106 where the data provider of the user personal data is located; receiving an operation decryption result fed back by the data provider server 106 according to the homomorphic operation result; and finally, determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a method for detecting a piracy is provided, which relates to the field of artificial intelligence, and is described by taking the application of the method to the detection server 104 in fig. 1 as an example, and includes the following steps:
step 201, when detecting the card swiping action of the user, acquiring user personal data of the user after homomorphic encryption processing.
The card swiping action specifically refers to the action of putting a magnetic card into or approaching to a magnetic card machine, reading the magnetic head, identifying information in the magnetic card to confirm the identity of a cardholder or increasing or decreasing storage resources in the magnetic card, for example, a buyer can transfer the resources to a seller in a card swiping mode in the shopping process. Homomorphic encryption is a cryptographic technique based on the theory of computational complexity of mathematical problems. The homomorphically encrypted data is processed to obtain an output, and the output is decrypted, the result of which is the same as the output result obtained by processing the unencrypted original data by the same method. The user personal data may include operator data or government public sector data such as FICO score, credit score, home asset, vehicle, work unit, monthly payroll, public accumulation payment, friendship, consumption transaction, etc. The user personal data is originally privacy data relative to the detection server 104, and after homomorphic encryption processing, the user personal data obtained through conversion is desensitized, and the processing of theft and brushing behavior detection can be performed at the detection server 104 on the premise of not exposing personal privacy.
Specifically, the scheme of the application is specifically used for detecting and identifying whether the card swiping behavior belongs to the theft swiping or not when the card swiping behavior occurs. Before detection begins, the user may perform a swipe action through terminal 102. In order to realize the resource transfer by swiping the card, the terminal 102 submits a corresponding resource transfer request to the detection server 104 after the swiping of the card is completed, the detection server 104 detects the swiping behavior, and after the detection, the subsequent resource transfer process can be executed. Therefore, the detection server 104 may determine that the card swiping behavior of the user is detected after receiving the resource transfer request of the terminal 102, and start the theft swiping behavior detection method. First, it is necessary to acquire user personal data of the user after the homomorphic encryption processing. In this case, the identification information of the user in the resource transfer request may be directly extracted, and the identification information is common to the detection server 104 and the data provider server 106. The detection server 104 may send a request to the data provider server 106 based on the identification information to obtain user personal data of the homomorphic encryption processed user provided by the data provider server 106. After receiving the request submitted by the detection server 104, the data provider server 106 may retrieve the original user personal data related to the user based on the identification information, then encrypt and desensitize the original user personal data by using a homomorphic encryption method, obtain the user personal data, and provide the user personal data to the detection server 104 as basic data for detecting the theft and brushing behavior.
Step 203, homomorphic operation is performed on the personal data of the user through the theft and brushing behavior detection model, so as to obtain a homomorphic operation result, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data.
The theft swiping behavior detection model is a machine learning model which is trained in advance and used for judging the risk that the current card swiping behavior belongs to the theft swiping behavior. For example, an initial model can be built through a random forest algorithm, and then the initial model is trained based on homomorphic encryption data of historical personal data, so that an available theft and brushing behavior detection model is obtained. The theft and brushing behavior detection model can perform homomorphic operation on the basis of homomorphic encrypted user personal data to obtain encrypted detection result related data. Homomorphic operation can calculate ciphertext data without decryption. The method and the device have the advantages that sensitive source data are not required to be destroyed, the data can be processed, the data source in the theft and brushing behavior detection process is expanded, and therefore the detection accuracy of the theft and brushing behavior detection is effectively improved.
Specifically, the scheme of the application detects the theft brushing behavior in a machine learning mode, so that in the detection process, a corresponding theft brushing behavior detection model needs to be trained first. Training the theft and brushing behavior detection model can be completed through homomorphic encryption data of historical personal data. In a specific embodiment, the theft behavior detection model may further introduce local personal data and related data of the card swiping behavior of the detection server 104, such as card swiping time, card swiping frequency, etc., as input data of the theft behavior detection model. And then, homomorphic operation is carried out by the theft and brushing behavior detection model, and homomorphic operation results are obtained. The user personal data in the ciphertext form obtained by homomorphic encryption is used as basic data of homomorphic operation, so that the user personal data is effectively utilized in the process of detecting the theft and brushing behaviors, and privacy leakage in the process of detecting the theft and brushing behaviors is avoided.
Step 205, feeding back homomorphic operation result to data provider of user personal data.
Step 207, receiving the operation decryption result fed back by the data provider according to the homomorphic operation result.
Specifically, the arithmetic decryption result is the result data obtained by decrypting and shrinking the homomorphic arithmetic result, and because homomorphic encryption is performed in the data provider server 106, the detection server 104 side does not relate to encryption and decryption processing related to the personal data of the user, and does not have a key for encrypting the data. Therefore, after the homomorphic operation result is obtained, the obtained homomorphic operation result needs to be fed back to the data provider server 106 where the data provider of the user personal data is located, and then the data provider server 106 performs corresponding decryption processing on the homomorphic operation result, and feeds back the decrypted result to the detection server 104. The detection server 104 receives the operation decryption result fed back by the data provider according to the homomorphic operation result, and performs subsequent behavior detection processing based on the operation decryption result.
Step 209, determining the theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
Specifically, after obtaining the arithmetic decryption result, the detection server 104 performs risk discrimination processing based on the arithmetic decryption result. Specifically, the risk level of the card swiping behavior of the user can be determined based on the operation decryption result, so that whether the card swiping behavior belongs to the theft swiping or not is judged based on the risk level of the card swiping behavior, and a theft swiping behavior detection result is obtained. Meanwhile, after the theft brushing behavior is detected, alarm processing can be carried out, so that the theft brushing risk is reduced.
According to the theft behavior detection method, when the card swiping behavior of the user is detected, user personal data of the user after homomorphic encryption processing is obtained; homomorphic operation is carried out on personal data of a user through a theft and brushing behavior detection model, and homomorphic operation results are obtained; feeding back homomorphic operation results to a data provider of personal data of the user; receiving an operation decryption result fed back by the data provider according to the homomorphic operation result; and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result. When the card swiping behavior of the user is detected, homomorphic operation is performed by acquiring homomorphic encrypted user personal data, and homomorphic operation results are submitted to the data provider for decryption, so that more comprehensive data can be introduced to detect the theft swiping behavior under the condition that user privacy data is not revealed, and accurate detection on the theft swiping behavior is realized.
In one embodiment, step 205 comprises: determining result feedback data according to the sum of homomorphic operation results and random numbers; and feeding back the data to a data provider of the personal data of the user. Step 207 comprises: receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number.
Specifically, in order to prevent the risk of disclosure caused by information interaction in the detection of the theft and brushing behavior, a random number may be added on the basis of the homomorphic operation result to obtain result feedback data. And then the result feedback data is fed back to the data provider, and the data provider also carries out homomorphic decryption on the basis of the result feedback data, so that the corresponding operation result cannot be determined from the data decryption result obtained by homomorphic decryption directly. The scheme of the application can subtract the original added random number from the data decryption result after receiving the data decryption result to obtain the corresponding operation decryption result. In the embodiment, the random number is added to the homomorphic operation result, and the random number is subtracted from the data decryption result, so that the leakage of the detection result can be avoided in the process of detecting the theft and brushing behavior, and the information safety of the user is ensured.
In one embodiment, before step 203, further comprising: acquiring historical personal data of a target user after homomorphic encryption; constructing model training data with data labels based on historical personal data; training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model.
Specifically, the scheme of the application also needs to complete the training of the theft and brushing behavior detection model, and the training process also needs the assistance of a data provider of the user personal data, and the data provider is mainly required to complete the encryption and decryption processing of the historical personal data. In the training process, a target user who can be used as a training sample can be determined based on the historical data. Historical personal data is then requested from the data provider for each target user. The data provider encrypts the historical personal data in a unified homomorphic encryption mode and feeds back homomorphic encrypted data. Therefore, the historical personal data of the target user after homomorphic encryption can be firstly obtained, and model training data with data labels are constructed based on the historical personal data, wherein the data labels specifically refer to label data for marking whether the target user has a theft and brushing behavior. The monitoring training of the initial theft and brushing behavior detection model can be realized through the model training data with the data labels, and the theft and brushing behavior detection model is obtained. In the training process, the model training data can be divided into a training set and a testing set, the training and testing of the initial theft and brushing behavior detection model are respectively completed, and finally the initial theft and brushing behavior detection model after the training is completed and passing the testing is used as a final theft and brushing behavior detection model. In this embodiment, training of the theft and brushing behavior detection model is completed through the homomorphic encrypted historical personal data of the target user, so that the accuracy of subsequent theft and brushing behavior detection can be effectively ensured.
In one embodiment, obtaining homomorphically encrypted historical personal data of the target user includes: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
Specifically, when historical personal data is requested, a user identification belonging to a target user shared with a data provider may be first determined. And then, based on the user identification, sending a data collaboration request of the target user to a data provider, wherein the data provider can obtain the user identification of the target user by analyzing the request. And searching the original historical personal data of the target user based on the analyzed user identification. And then, directly carrying out homomorphic encryption processing on the searched original historical personal data to obtain corresponding historical personal data, and finally feeding the obtained historical personal data back to a request end carrying the theft and brushing behavior detection, wherein the request end can construct model training data on the basis of the historical personal data of a received data provider to finish training an initial theft and brushing behavior detection model. In this embodiment, the data provider is requested to provide the historical personal data for model training through the data collaboration request, so that the efficiency of obtaining the historical personal data is effectively ensured, and the training efficiency of the model is improved.
In one embodiment, constructing model training data with data tags based on historical personal data includes: acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained.
Specifically, in the scheme of the application, besides the user personal data saved by the data provider, the theft and brushing behavior detection can be performed by means of target user data of the user on the local server. First, model training data may be constructed based on target user data and historical personal data, such that the constructed model training data may include both encrypted user personal data and unencrypted user personal data. And the card swiping behavior contained in the card swiping historical data can judge whether the target user has the stolen card swiping behavior, so that the data tag of the corresponding card swiping behavior of the target user is directly determined based on the card swiping historical data, and the data tag is added to the model training data to obtain the model training data with the data tag. And then, the training, testing and other processing of the initial theft and brushing behavior detection model can be completed based on the model training data with the data labels. In this embodiment, the model training data is constructed by the target user data and the card swiping history data of the target user in the history data, and the model training data can be constructed by combining the card swiping history behaviors of the user on the basis of effectively considering the local data, so that the detection accuracy of the theft swiping behavior detection based on the theft swiping behavior detection model is ensured.
In one embodiment, as shown in fig. 3, the method further comprises:
step 302, determining a theft swiping risk level of the card swiping action based on the theft swiping action detection result.
Step 304, generating a risk prompt message corresponding to the robber brushing risk level.
And 306, feeding back a risk prompt message to an auditing terminal of the card swiping action.
Specifically, the final detection result of the theft and brushing behavior may be specifically expressed in the form of risk parameters, where different risk parameters correspond to different risk levels, for example, the risk parameters may be 0 to 100 points, and the risk levels include 1 to 5 points, where the 1-point risk is 80 to 100 points, the 2-point risk is 60 to 79 points, the 3-point risk is 40 to 59 points, the 4-point risk is 20 to 39 points, and the 5-point risk is 0 to 20 points. After the risk parameters are obtained, a theft swiping risk level of the card swiping behavior can be determined based on the risk parameters. If the final score is 85 points, the robber brushing risk level is determined to be 1, and no risk is represented, and risk prompt is not needed. If the final risk rating is 3/4/5, the risk prompt message corresponding to the current risk level of the robber is required to be generated, the risk level of the robber is marked, the risk prompt message is generated, and the risk prompt message is submitted to an audit terminal of the card swiping behavior. The auditing terminal can audit the theft risk in a finer way by manpower or other modes, so that the theft risk is avoided. In this embodiment, through the detection of robber brushing risk level to carry out risk suggestion through risk suggestion message, can in time carry out the suggestion that robber brushing risk is relevant, reduce robber brushing risk.
In one embodiment, the method for detecting the brushing behavior comprises the following steps: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider. Acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained. Training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model. When the card swiping behavior of the user is detected, acquiring user personal data of the user after homomorphic encryption processing; and carrying out homomorphic operation on the personal data of the user through the theft and brushing behavior detection model to obtain homomorphic operation results. Determining result feedback data according to the sum of homomorphic operation results and random numbers; and feeding back the data to a data provider of the personal data of the user. Receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number. And determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result. Determining a theft swiping risk level of the card swiping behavior based on a theft swiping behavior detection result; generating a risk prompt message corresponding to the robber brushing risk level; and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a theft behavior detection device for realizing the theft behavior detection method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation of the embodiment of the device for detecting a theft behavior provided in the following may be referred to the limitation of the method for detecting a theft behavior hereinabove, and will not be described herein.
In one embodiment, as shown in fig. 4, there is provided a theft behavior detection device, including:
the data acquisition module 401 is configured to acquire user personal data of the user after homomorphic encryption processing when detecting a card swiping behavior of the user.
The homomorphic operation module 403 is configured to perform homomorphic operation on personal data of a user through a theft and swipe behavior detection model, so as to obtain a homomorphic operation result, where the theft and swipe behavior detection model is obtained by training homomorphic encrypted data of historical personal data.
And the data feedback module 405 is used for feeding back the homomorphic operation result to the data provider of the personal data of the user.
The data receiving module 407 is configured to receive an operation decryption result fed back by the data provider according to the homomorphic operation result.
The behavior detection module 409 is configured to determine a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In one embodiment, the data feedback module 405 is specifically configured to: determining result feedback data according to the sum of homomorphic operation results and random numbers; and feeding back the data to a data provider of the personal data of the user. The data receiving module 407 is specifically configured to: receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number.
In one embodiment, the method further comprises a model training module for: acquiring historical personal data of a target user after homomorphic encryption; constructing model training data with data labels based on historical personal data; training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model.
In one embodiment, the model training module is further to: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
In one embodiment, the model training module is further to: acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained.
In one embodiment, the system further comprises a message alarm module for: determining a theft swiping risk level of the card swiping behavior based on a theft swiping behavior detection result; generating a risk prompt message corresponding to the robber brushing risk level; and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
The above-mentioned various modules in the theft and brushing behavior detection device may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used for storing data related to the detection of the theft and brushing behavior. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by a processor, implements a method of detecting a piracy.
It will be appreciated by those skilled in the art that the structure shown in fig. 5 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided comprising a memory and a processor, the memory having stored therein a computer program, the processor when executing the computer program performing the steps of:
and when the card swiping behavior of the user is detected, acquiring user personal data of the user after homomorphic encryption processing.
And carrying out homomorphic operation on the personal data of the user through the theft and brushing behavior detection model to obtain homomorphic operation results, wherein the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data.
And feeding back homomorphic operation results to a data provider of personal data of the user.
And receiving an operation decryption result fed back by the data provider according to the homomorphic operation result.
And determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In one embodiment, the processor when executing the computer program further performs the steps of: determining result feedback data according to the sum of homomorphic operation results and random numbers; the feedback result feeds back data to a data provider of personal data of the user; receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring historical personal data of a target user after homomorphic encryption; constructing model training data with data labels based on historical personal data; training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model.
In one embodiment, the processor when executing the computer program further performs the steps of: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
In one embodiment, the processor when executing the computer program further performs the steps of: acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained.
In one embodiment, the processor when executing the computer program further performs the steps of: determining a theft swiping risk level of the card swiping behavior based on a theft swiping behavior detection result; generating a risk prompt message corresponding to the robber brushing risk level; and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
and when the card swiping behavior of the user is detected, acquiring user personal data of the user after homomorphic encryption processing.
And carrying out homomorphic operation on the personal data of the user through the theft and brushing behavior detection model to obtain homomorphic operation results, wherein the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data.
And feeding back homomorphic operation results to a data provider of personal data of the user.
And receiving an operation decryption result fed back by the data provider according to the homomorphic operation result.
And determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining result feedback data according to the sum of homomorphic operation results and random numbers; the feedback result feeds back data to a data provider of personal data of the user; receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical personal data of a target user after homomorphic encryption; constructing model training data with data labels based on historical personal data; training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model.
In one embodiment, the computer program when executed by the processor further performs the steps of: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a theft swiping risk level of the card swiping behavior based on a theft swiping behavior detection result; generating a risk prompt message corresponding to the robber brushing risk level; and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
and when the card swiping behavior of the user is detected, acquiring user personal data of the user after homomorphic encryption processing.
And carrying out homomorphic operation on the personal data of the user through the theft and brushing behavior detection model to obtain homomorphic operation results, wherein the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data.
And feeding back homomorphic operation results to a data provider of personal data of the user.
And receiving an operation decryption result fed back by the data provider according to the homomorphic operation result.
And determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining result feedback data according to the sum of homomorphic operation results and random numbers; the feedback result feeds back data to a data provider of personal data of the user; receiving a data decryption result fed back by a data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data; and determining an operation decryption result based on the difference between the data decryption result and the random number.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring historical personal data of a target user after homomorphic encryption; constructing model training data with data labels based on historical personal data; training the initial theft behavior detection model based on model training data with data labels to obtain the theft behavior detection model.
In one embodiment, the computer program when executed by the processor further performs the steps of: sending a data collaboration request of a target user to a data provider; and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
In one embodiment, the computer program when executed by the processor further performs the steps of: acquiring target user data and card swiping historical data of a target user in the historical data; model training data is built based on target user data and historical personal data, and data tags are added to the model training data through card swiping historical data, so that model training data with the data tags is obtained.
In one embodiment, the computer program when executed by the processor further performs the steps of: determining a theft swiping risk level of the card swiping behavior based on a theft swiping behavior detection result; generating a risk prompt message corresponding to the robber brushing risk level; and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.

Claims (10)

1. A method for detecting a piracy, the method comprising:
when the card swiping behavior of a user is detected, acquiring user personal data of the user after homomorphic encryption processing;
homomorphic operation is carried out on the user personal data through a theft and brushing behavior detection model, so that homomorphic operation results are obtained, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
Feeding back the homomorphic operation result to a data provider of the user personal data;
receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
2. The method of claim 1, wherein the feeding back the homomorphic operation result to the data provider of the user personal data comprises:
determining result feedback data according to the sum of the homomorphic operation result and the random number;
feeding back the result feedback data to a data provider of the user personal data;
the receiving the operation decryption result fed back by the data provider according to the homomorphic operation result comprises the following steps:
receiving a data decryption result fed back by the data provider, wherein the data decryption result is obtained by homomorphic decryption of the result feedback data;
and determining an operation decryption result based on the difference between the data decryption result and the random number.
3. The method according to claim 1, wherein before the homomorphic operation is performed on the personal data of the user by using the piracy detection model, the method further comprises:
Acquiring historical personal data of a target user after homomorphic encryption;
constructing model training data with data labels based on the historical personal data;
and training the initial theft and brushing behavior detection model based on the model training data with the data tag to obtain the theft and brushing behavior detection model.
4. A method according to claim 3, wherein said obtaining homomorphically encrypted historical personal data of the target user comprises:
transmitting a data collaboration request of the target user to the data provider;
and receiving historical personal data of the target user fed back by the data provider based on the data collaboration request, wherein the historical personal data is obtained by homomorphic encryption of the original historical personal data of the target user by the data provider.
5. The method of claim 3, wherein said constructing model training data with data tags based on said historical personal data comprises:
acquiring target user data and card swiping historical data of a target user in the historical data;
and constructing model training data based on the target user data and the historical personal data, and adding a data tag to the model training data through the swipe card historical data to obtain model training data with the data tag.
6. The method according to any one of claims 1 to 5, further comprising:
determining a theft swiping risk level of the card swiping behavior based on the theft swiping behavior detection result;
generating a risk prompt message corresponding to the theft and brushing risk level;
and feeding back the risk prompt message to an auditing terminal of the card swiping behavior.
7. A theft behavior detection device, the device comprising:
the data acquisition module is used for acquiring user personal data of the user after homomorphic encryption processing when detecting the card swiping behavior of the user;
the homomorphic operation module is used for carrying out homomorphic operation on the user personal data through the theft and brushing behavior detection model to obtain homomorphic operation results, and the theft and brushing behavior detection model is obtained by training homomorphic encryption data of historical personal data;
the data feedback module is used for feeding back the homomorphic operation result to a data provider of the user personal data;
the data receiving module is used for receiving an operation decryption result fed back by the data provider according to the homomorphic operation result;
and the behavior detection module is used for determining a theft swiping behavior detection result of the card swiping behavior according to the operation decryption result.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
CN202311153887.3A 2023-09-07 2023-09-07 Method and device for detecting theft and brushing behaviors, computer equipment and storage medium Pending CN117391701A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311153887.3A CN117391701A (en) 2023-09-07 2023-09-07 Method and device for detecting theft and brushing behaviors, computer equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311153887.3A CN117391701A (en) 2023-09-07 2023-09-07 Method and device for detecting theft and brushing behaviors, computer equipment and storage medium

Publications (1)

Publication Number Publication Date
CN117391701A true CN117391701A (en) 2024-01-12

Family

ID=89465628

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311153887.3A Pending CN117391701A (en) 2023-09-07 2023-09-07 Method and device for detecting theft and brushing behaviors, computer equipment and storage medium

Country Status (1)

Country Link
CN (1) CN117391701A (en)

Similar Documents

Publication Publication Date Title
US11556671B2 (en) Systems and methods of determining compromised identity information
CN111666576B (en) Data processing model generation method and device, and data processing method and device
US20190258927A1 (en) Data exchange method, data exchange device and computing device
US11899816B2 (en) Batch tokenization service
CN108681676B (en) Data management method and apparatus, system, electronic device, program, and storage medium
CN110688662A (en) Sensitive data desensitization and inverse desensitization method and electronic equipment
CN113326517A (en) System and method for detecting sensitive information leakage while preserving privacy
CN110729028A (en) Health data processing method and device, electronic equipment and storage medium
US11966488B2 (en) De-tokenization patterns and solutions
CN111861099A (en) Model evaluation method and device of federal learning model
CN111461731A (en) Block chain monitoring system and method applied to financial transactions
CN114386058A (en) Model file encryption and decryption method and device
CN113792307A (en) Seal management method and device and electronic equipment
CN115409512A (en) Abnormal information detection method, abnormal information detection device, computer equipment and storage medium
CN117391701A (en) Method and device for detecting theft and brushing behaviors, computer equipment and storage medium
CN113159952A (en) Method, system, device and storage medium for storing digital assets based on block chain
Akanchha Exploring a robust machine learning classifier for detecting phishing domains using SSL certificates
US11531739B1 (en) Authenticating user identity based on data stored in different locations
CN117421709A (en) Function service method, device, computer equipment and storage medium of application program
CN117493335A (en) Report processing method, report processing device, report processing equipment, storage medium and computer program product
CN117034345A (en) Data desensitization method, device, computer equipment and storage medium
CN116647384A (en) Information display method, information display device, computer equipment and storage medium
CN117436057A (en) Security verification method, security verification device, computer equipment and storage medium
CN117611165A (en) Abnormal object detection method, device, computer equipment and storage medium
CN117240497A (en) User account anomaly evaluation method, device, computer equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination