CN112862493B - Intelligent Pompe deception detection method, device, terminal and storage medium - Google Patents
Intelligent Pompe deception detection method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN112862493B CN112862493B CN202110110510.4A CN202110110510A CN112862493B CN 112862493 B CN112862493 B CN 112862493B CN 202110110510 A CN202110110510 A CN 202110110510A CN 112862493 B CN112862493 B CN 112862493B
- Authority
- CN
- China
- Prior art keywords
- intelligent
- contract
- account
- fraud
- pompe
- 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.)
- Active
Links
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/50—Monitoring users, programs or devices to maintain the integrity of platforms, e.g. of processors, firmware or operating systems
- G06F21/55—Detecting local intrusion or implementing counter-measures
- G06F21/56—Computer malware detection or handling, e.g. anti-virus arrangements
- G06F21/562—Static detection
- G06F21/563—Static detection by source code analysis
Abstract
The application discloses an intelligent Pompe fraud detection method, an intelligent Pompe fraud detection device, a terminal and a storage medium.
Description
Technical Field
The present application relates to the field of block chaining technologies, and in particular, to an intelligent pompe cheating detecting method, apparatus, terminal, and storage medium.
Background
With the development of block chain technology, cryptocurrency platforms are widely used worldwide. Pompe frauds began to appear in the form of intelligent contracts, such block chain based pompe frauds being referred to as intelligent pompe frauds, and the corresponding intelligent contracts being referred to as intelligent pompe frauds contracts.
Due to the anonymity of the cryptocurrency, the account of the user on the blockchain can be separated from the real identity of the user; because of the public nature of cryptocurrency, users worldwide can use cryptocurrency; transactions that have been made and recorded on the blockchain are difficult to withdraw due to the hard-to-tamper nature of cryptocurrency. On the one hand, these features make cryptocurrency an important application, and on the other hand, they also reduce the criminal cost of a lawbreaker. So that criminals can pay the illegal income out by anonymously issuing illegal fraud contracts on the cryptocurrency platform and carrying out money laundering through the mixed currency service.
The current intelligent PON cheat detection mainly judges whether the characteristics of the PON cheat are met by collecting intelligent contracts for disclosing source codes and manually checking the source codes, but the detection mode is limited by the abundance degree of characteristic representation in the aspect of byte codes, and the technical problem of unstable identification accuracy exists.
Disclosure of Invention
The application provides an intelligent Pompe fraud detection method, an intelligent Pompe fraud detection device, a terminal and a storage medium, and aims to solve the technical problem that the accuracy of the existing intelligent Pompe fraud detection technology is unstable.
The first aspect of the application provides an intelligent colossal deception detection method, which comprises the following steps:
s1, acquiring a target intelligent contract to be detected, and extracting contract characteristics of the target intelligent contract, wherein the contract characteristics comprise: bytecode features and creator account features;
s2, taking the contract characteristics as input variables of an intelligent Pompe deception contract detection model, and obtaining a first detection result output by the intelligent Pompe deception contract detection model through the operation of the intelligent Pompe deception contract detection model;
s3, calculating association degree values between each account and known fraud accounts according to the obtained blockchain transaction records and the known fraud accounts, and obtaining a money laundering relationship account set according to the association degree values, the blockchain transaction records and the known fraud accounts and in combination with an illegal transaction classification model, wherein the association degree values are obtained by conversion according to distance values between the accounts and the known fraud accounts;
s4, using the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraud contract detection model, and obtaining a second detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model, wherein the money laundering suspected account includes: a money laundering relationship account within the money laundering relationship account set, and/or an account adjacent to the money laundering relationship account;
and S5, if the first detection result is consistent with the second detection result, outputting an intelligent Pompe fraud detection result of the target intelligent contract, if the first detection result is inconsistent with the second detection result, updating the money laundering relationship account set according to the second detection result, then using the current second detection result as a new first detection result, and then returning to the step S4 so as to obtain a new second detection result according to the updated money laundering relationship account set.
Preferably, the configuration process of the intelligent pompe fraud contract detection model specifically includes:
and inputting the contract feature samples into an initial regression tree classification model based on the obtained contract feature samples, and performing model training on the initial regression tree classification model to obtain the intelligent Pompe deception contract detection model.
Preferably, the initial regression tree classification model is specifically an XGBoost classification model.
Preferably, the step S3 specifically includes:
according to the acquired blockchain transaction records, combining with known fraud accounts, calculating distance values between each account and the known fraud accounts, and converting the distance values into association degree values;
determining an illegal transaction record set in the blockchain transaction records by taking the relevance degree value as an input variable of an illegal transaction classification model;
and clustering the illegal transaction record set, and generating a money laundering relation account set from accounts in the same cluster based on a clustering result.
A second aspect of the present application provides an intelligent pompe fraud detection apparatus, including:
the contract feature extraction unit is used for acquiring a target intelligent contract to be detected and extracting contract features of the target intelligent contract, and the contract features comprise: bytecode features and creator account features;
the first detection unit is used for taking the contract characteristics as input variables of an intelligent Pompe fraud contract detection model so as to obtain a first detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model;
the system comprises a relation account set obtaining unit, a money laundering relation account set obtaining unit and a money laundering processing unit, wherein the relation account set obtaining unit is used for calculating a correlation degree value between each account and a known fraud account according to obtained block chain transaction records and the known fraud account, and obtaining the money laundering relation account set by combining an illegal transaction classification model according to the correlation degree value, the block chain transaction records and the known fraud account, wherein the correlation degree value is obtained by conversion according to a distance value between the account and the known fraud account;
the second detection unit is used for taking the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraud contract detection model, and obtaining a second detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model, wherein the money laundering suspected account is a money laundering relationship account in the money laundering relationship account set or an account adjacent to the money laundering relationship account;
and a detection result comparison unit, configured to output an intelligent pompe fraud detection result of the target intelligent contract if the first detection result is consistent with the second detection result, update the money laundering relationship account set according to the second detection result if the first detection result is inconsistent with the second detection result, then use the current second detection result as a new first detection result, and then return to step S4, so as to obtain a new second detection result according to the updated money laundering relationship account set.
Preferably, the method further comprises the following steps:
and the intelligent Pompe fraud contract detection model training unit is used for inputting the contract feature samples into an initial regression tree classification model based on the acquired contract feature samples so as to obtain the intelligent Pompe fraud contract detection model by performing model training on the initial regression tree classification model.
Preferably, the initial regression tree classification model is specifically an XGBoost classification model.
Preferably, the relationship account set obtaining unit is specifically configured to:
according to the acquired blockchain transaction records, combining with known fraud accounts, calculating distance values between each account and the known fraud accounts, and converting the distance values into association degree values;
determining an illegal transaction record set in the blockchain transaction records by taking the relevance degree value as an input variable of an illegal transaction classification model;
and clustering the illegal transaction record set, and generating a money laundering relation account set from accounts in the same cluster based on a clustering result.
A third aspect of the present application provides an intelligent pompe deception office detection terminal, including: a memory and a processor;
the memory is used for storing program codes, and the program codes correspond to the intelligent Pompe fraud detection method mentioned in the first aspect of the application;
the processor is configured to execute the program code.
A fourth aspect of the present application provides a storage medium, wherein the storage medium stores program codes corresponding to an intelligent pompe fraud detection method according to the first aspect of the present application.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides an intelligent colossal deception detection method, which comprises the following steps: s1, acquiring a target intelligent contract to be detected, and extracting contract characteristics of the target intelligent contract, wherein the contract characteristics comprise: bytecode features and creator account features; s2, taking the contract characteristics as input variables of an intelligent Pompe deception contract detection model, and obtaining a first detection result output by the intelligent Pompe deception contract detection model through the operation of the intelligent Pompe deception contract detection model; s3, calculating association degree values between each account and known fraud accounts according to the obtained blockchain transaction records and the known fraud accounts, and obtaining a money laundering relationship account set according to the association degree values, the blockchain transaction records and the known fraud accounts and in combination with an illegal transaction classification model, wherein the association degree values are obtained by conversion according to distance values between the accounts and the known fraud accounts; s4, using the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraud contract detection model, and obtaining a second detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model, wherein the money laundering suspected account includes: a money laundering relationship account within the money laundering relationship account set, and/or an account adjacent to the money laundering relationship account; and S5, if the first detection result is consistent with the second detection result, outputting an intelligent Pompe fraud detection result of the target intelligent contract, if the first detection result is inconsistent with the second detection result, updating the money laundering relationship account set according to the second detection result, then using the current second detection result as a new first detection result, and then returning to the step S4 so as to obtain a new second detection result according to the updated money laundering relationship account set.
According to the method and the device, detection of the Pompe fraudster contract and detection of the money laundering mode account relation are combined, iterative cross detection is carried out on the two detection results, the detection accuracy is improved, the final result is more reliable, and the technical problem that the accuracy of the existing intelligent Pompe fraudster detection technology is unstable is solved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
FIG. 1 is a schematic flow chart illustrating an embodiment of an intelligent Pompe fraudster detection method provided by the present application;
FIG. 2 is a schematic flow chart illustrating another embodiment of an intelligent Pompe fraudster detection method provided by the present application;
fig. 3 is a schematic structural diagram of an embodiment of an intelligent pompe fraud detection apparatus provided by the present application.
Detailed Description
The embodiment of the application provides an intelligent Pompe fraudster detection method, an intelligent Pompe fraudster detection device, a terminal and a storage medium, and is used for solving the technical problem that the accuracy of the existing intelligent Pompe fraudster detection technology is unstable.
In order to make the objects, features and advantages of the present invention more apparent and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the embodiments described below are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a first embodiment of the present application provides an intelligent pompe fraud detection method, including:
s1, acquiring the target intelligent contract to be detected, and extracting contract characteristics of the target intelligent contract, wherein the contract characteristics comprise: bytecode features and creator account features.
And S2, taking the contract characteristics as input variables of the intelligent Poinch deception contract detection model, and obtaining a first detection result output by the intelligent Poinch deception contract detection model through the operation of the intelligent Poinch deception contract detection model.
It should be noted that, according to the detection method provided by the present application, first, a target intelligent contract for detecting a pompe deception contract is performed as needed, and contract features of the target intelligent contract are extracted. And then, the contract characteristics are used as input variables of the intelligent Poinch deception contract detection model, and a first detection result output by the intelligent Poinch deception contract detection model is obtained through the operation of the intelligent Poinch deception contract detection model.
And S3, calculating the association degree value between each account and the known fraud account according to the obtained blockchain transaction record and the known fraud account, and obtaining a money laundering relationship account set according to the association degree value, the blockchain transaction record and the known fraud account by combining an illegal transaction classification model, wherein the association degree value is obtained by conversion according to the distance value between the account and the known fraud account.
It should be noted that, according to the obtained blockchain transaction records and known fraud accounts, the association degree value between each account and the known fraud account is calculated, and it can be understood that the blockchain transaction records include the following information: the method comprises the steps that account information, transaction times, transaction amount, account balance of two transaction parties, a transaction initiation timestamp, time difference between the first transaction and the last transaction of the two transaction parties, average time of double-issue transaction initiation of the transaction and the like are obtained on the basis of the information obtained by the block chain transaction records, and the known fraud accounts are combined, so that whether the accounts in the transaction records have direct transactions with the known fraud accounts or not and the distance between each account and the known fraud accounts can be known, and the corresponding association degree value is obtained through conversion according to the distance value between the account and the known fraud accounts.
The known fraud account mentioned in this embodiment specifically refers to an account that has been determined to be an intelligent pompe fraud, and the contract of the account can be regarded as an intelligent pompe fraud contract, and specifically may be a fraud account determined according to the obtained detection result by executing the method provided by the present application, or a fraud account determined by other means.
And then, combining an illegal transaction classification model according to the association degree value, the block chain transaction record and the known fraud account to obtain a money laundering relation account set.
S4, using the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraudster contract detection model, and obtaining a second detection result output by the intelligent Pompe fraudster contract detection model through the operation of the intelligent Pompe fraudster contract detection model, wherein the money laundering suspected account includes: a money laundering relationship account within the set of money laundering relationship accounts, and/or an account adjacent to the money laundering relationship account.
It should be noted that one or more money laundering suspected accounts are determined based on the account information of the money laundering relationship account set obtained in the above steps, the creator account characteristics of the money laundering suspected accounts are used as supplementary parameters, and the contract characteristics are used as input variables of the intelligent pompe fraud contract detection model, so that a second detection result output by the intelligent pompe fraud contract detection model is obtained through the operation of the intelligent pompe fraud contract detection model.
And S5, if the first detection result is consistent with the second detection result, outputting an intelligent Pompe fraud detection result of the target intelligent contract, if the first detection result is inconsistent with the second detection result, updating the money laundering relationship account set according to the second detection result, then using the current second detection result as a new first detection result, and then returning to the step S4 so as to obtain a new second detection result according to the updated money laundering relationship account set.
And finally, according to the comparison result of the first detection result and the second detection result, if the two detection results are changed, updating the money laundering relationship account set according to the second detection result, re-generating the money laundering relationship account set, using the current second detection result as a new first detection result, and returning to the step S4 so as to obtain a new second detection result according to the updated money laundering relationship account set until the first detection result is consistent with the second detection result or the iteration number reaches the upper limit.
For the difference between the two detection results, the updating of the money laundering relationship account set according to the second detection result in the embodiment includes: from none to some, or from some to some. Taking the first example, the first detection result of the target intelligent contract mentioned in this embodiment is intended to show that the target intelligent contract does not belong to the intelligent pompe fraud contract, but the second detection result shows that the target intelligent contract belongs to the intelligent pompe fraud contract, at this time, the account corresponding to the target intelligent contract is regarded as a known fraud account, and the association degree value of each account is recalculated, so as to achieve the purpose of updating the money laundering relationship account set. In another case, the account corresponding to the target intelligent contract is regarded as a normal account, and the rest is the same, which is not described herein again
If the detection result is not changed, the result is considered to be the final credible result, and the detection results of the Pompe fraudster contract and the money laundering mode are obtained.
According to the embodiment of the application, detection of the Pompe fraudster contract and detection of the money laundering mode account relation are combined, iterative cross detection is carried out on the two detection results, the detection accuracy is improved, the final result is more reliable, and the technical problem that the accuracy of the detection of the existing intelligent Pompe fraudster detection technology is unstable is solved.
The above is a detailed description of a first embodiment of an intelligent pompe fraud detection method provided by the present application, and the following is a detailed description of a second embodiment of the intelligent pompe fraud detection method provided by the present application.
Referring to fig. 2, based on the first embodiment, a second embodiment of the present application provides an intelligent pointcast cheating detection method, which specifically includes:
further, the configuration process of the intelligent pompe fraud contract detection model specifically comprises the following steps:
and S0, inputting the contract feature samples into the initial regression tree classification model based on the obtained contract feature samples, and performing model training on the initial regression tree classification model to obtain the intelligent Pompe deception contract detection model.
Further, the initial regression tree classification model is specifically an XGBoost classification model.
Further, step S3 specifically includes:
and S31, calculating the distance value between each account and the known fraud account according to the acquired blockchain transaction record and in combination with the known fraud account, and converting the distance value into an association degree value.
And S32, determining an illegal transaction record set in the blockchain transaction records by taking the degree of association value as an input variable of the illegal transaction classification model.
The illegal transaction classification model of the embodiment is preferably an XGBoost classification model.
And S33, clustering the illegal transaction record sets, and generating a money laundering relation account set from accounts in the same cluster based on the clustering result. Specifically, the adjacent illegal transaction sets are extracted, and if the distance of the illegal transactions in one set is small enough, the transaction set with the distance smaller than the preset set distance threshold value from the set is considered to belong to a money laundering mode.
The above is a detailed description of a second embodiment of the intelligent pompe fraud detection method provided by the present application, and the following is a detailed description of an embodiment of the intelligent pompe fraud detection apparatus provided by the present application.
Referring to fig. 3, a third embodiment of the present application provides an intelligent pompe fraud detection apparatus, including:
the contract feature extraction unit a1 is configured to acquire a target intelligent contract to be detected, and extract contract features of the target intelligent contract, where the contract features include: bytecode features and creator account features;
the first detection unit A2 is used for taking the contract characteristics as input variables of the intelligent Poinch deception contract detection model, and obtaining a first detection result output by the intelligent Poinch deception contract detection model through the operation of the intelligent Poinch deception contract detection model;
the relation account set obtaining unit A3 is used for calculating the association degree value between each account and the known fraud account according to the obtained blockchain transaction record and the known fraud account, and obtaining a money laundering relation account set according to the association degree value, the blockchain transaction record and the known fraud account by combining an illegal transaction classification model, wherein the association degree value is obtained by conversion according to the distance value between the account and the known fraud account;
the second detection unit A4 is configured to use account characteristics and contract characteristics of a creator of the money laundering suspected account as input variables of the intelligent Poinch deception contract detection model, and obtain a second detection result output by the intelligent Poinch deception contract detection model through operation of the intelligent Poinch deception contract detection model, where the money laundering suspected account is a money laundering relationship account in the money laundering relationship account set or an account adjacent to the money laundering relationship account;
and the detection result comparison unit A5 is configured to output an intelligent Pompe fraud detection result of the target intelligent contract if the first detection result is consistent with the second detection result, update the money laundering relationship account set according to the second detection result if the first detection result is inconsistent with the second detection result, use the current second detection result as a new first detection result, and then return to step S4 to obtain a new second detection result according to the updated money laundering relationship account set.
Further, still include:
and the intelligent Pompe fraud contract detection model training unit A0 is used for inputting the contract feature samples into the initial regression tree classification model based on the obtained contract feature samples, so as to obtain the intelligent Pompe fraud contract detection model by performing model training on the initial regression tree classification model.
Further, the initial regression tree classification model is specifically an XGBoost classification model.
Further, the relationship account set obtaining unit a3 is specifically configured to:
according to the acquired blockchain transaction records, combining with known fraud accounts, calculating distance values between each account and the known fraud accounts, and converting the distance values into association degree values;
determining an illegal transaction record set in the block chain transaction records by taking the degree of association value as an input variable of an illegal transaction classification model;
and clustering the illegal transaction record sets, and generating a money laundering relation account set from accounts in the same cluster based on a clustering result.
The above is a detailed description of an embodiment of an intelligent pompe fraud detection apparatus provided by the present application, and the following is a detailed description of an embodiment of an intelligent pompe fraud detection terminal and an embodiment of a storage medium provided by the present application.
A fourth embodiment of the present application provides an intelligent detecting terminal for pompe deception bureau, including: a memory and a processor;
the memory is used for storing program codes, and the program codes correspond to an intelligent Pompe fraud detection method mentioned in the first embodiment or the second embodiment of the application;
the processor is configured to execute the program code to implement an intelligent pointcast fraud detection method according to the first or second embodiment of the present application.
A fifth embodiment of the present application provides a storage medium, wherein the storage medium stores program codes corresponding to an intelligent pompe fraud detection method according to the first or second embodiment of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (8)
1. An intelligent colossal fraud detection method, comprising:
s1, acquiring a target intelligent contract to be detected, and extracting contract characteristics of the target intelligent contract, wherein the contract characteristics comprise: bytecode features and creator account features;
s2, taking the contract characteristics as input variables of an intelligent Pompe deception contract detection model, and obtaining a first detection result output by the intelligent Pompe deception contract detection model through the operation of the intelligent Pompe deception contract detection model; the configuration process of the intelligent pompe fraud contract detection model specifically comprises the following steps:
inputting the contract feature samples into an initial regression tree classification model based on the obtained contract feature samples, and performing model training on the initial regression tree classification model to obtain the intelligent Pompe deception contract detection model;
s3, calculating association degree values between each account and known fraud accounts according to the obtained blockchain transaction records and the known fraud accounts, and obtaining a money laundering relationship account set according to the association degree values, the blockchain transaction records and the known fraud accounts and in combination with an illegal transaction classification model, wherein the association degree values are obtained by conversion according to distance values between the accounts and the known fraud accounts;
s4, using the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraud contract detection model, and obtaining a second detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model, wherein the money laundering suspected account includes: a money laundering relationship account within the money laundering relationship account set, and/or an account adjacent to the money laundering relationship account;
and S5, if the first detection result is consistent with the second detection result, outputting an intelligent Pompe fraud detection result of the target intelligent contract, if the first detection result is inconsistent with the second detection result, updating the money laundering relationship account set according to the second detection result, then using the current second detection result as a new first detection result, and then returning to the step S4 so as to obtain a new second detection result according to the updated money laundering relationship account set.
2. The intelligent pompe fraud detection method of claim 1, wherein the initial regression tree classification model is specifically an XGBoost classification model.
3. The intelligent pompe fraud detection method of claim 1, wherein the S3 specifically comprises:
according to the acquired blockchain transaction records, combining with known fraud accounts, calculating distance values between each account and the known fraud accounts, and converting the distance values into association degree values;
determining an illegal transaction record set in the blockchain transaction records by taking the relevance degree value as an input variable of an illegal transaction classification model;
and clustering the illegal transaction record set, and generating a money laundering relation account set from accounts in the same cluster based on a clustering result.
4. An intelligent PONYS deception detection device, comprising:
the contract feature extraction unit is used for acquiring a target intelligent contract to be detected and extracting contract features of the target intelligent contract, and the contract features comprise: bytecode features and creator account features;
the first detection unit is used for taking the contract characteristics as input variables of an intelligent Pompe fraud contract detection model so as to obtain a first detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model; the intelligent pompe fraud contract detection model is configured based on an intelligent pompe fraud contract detection model training unit, and the configuration process specifically comprises the following steps:
inputting the contract feature samples into an initial regression tree classification model based on the obtained contract feature samples, and performing model training on the initial regression tree classification model to obtain the intelligent Pompe deception contract detection model;
the system comprises a relation account set obtaining unit, a money laundering relation account set obtaining unit and a money laundering processing unit, wherein the relation account set obtaining unit is used for calculating a correlation degree value between each account and a known fraud account according to obtained block chain transaction records and the known fraud account, and obtaining the money laundering relation account set by combining an illegal transaction classification model according to the correlation degree value, the block chain transaction records and the known fraud account, wherein the correlation degree value is obtained by conversion according to a distance value between the account and the known fraud account;
the second detection unit is used for taking the creator account characteristics and the contract characteristics of the money laundering suspected account as input variables of the intelligent Pompe fraud contract detection model, and obtaining a second detection result output by the intelligent Pompe fraud contract detection model through the operation of the intelligent Pompe fraud contract detection model, wherein the money laundering suspected account is a money laundering relationship account in the money laundering relationship account set or an account adjacent to the money laundering relationship account;
and a detection result comparison unit, configured to output an intelligent pompe fraud detection result of the target intelligent contract if the first detection result is consistent with the second detection result, update the money laundering relationship account set according to the second detection result if the first detection result is inconsistent with the second detection result, then use the current second detection result as a new first detection result, and then return to step S4, so as to obtain a new second detection result according to the updated money laundering relationship account set.
5. The intelligent pompe fraud detection apparatus of claim 4, wherein the initial regression tree classification model is specifically an XGboost classification model.
6. The intelligent pompe fraud detection apparatus of claim 4, wherein the relational account set obtaining unit is specifically configured to:
according to the acquired blockchain transaction records, combining with known fraud accounts, calculating distance values between each account and the known fraud accounts, and converting the distance values into association degree values;
determining an illegal transaction record set in the blockchain transaction records by taking the relevance degree value as an input variable of an illegal transaction classification model;
and clustering the illegal transaction record set, and generating a money laundering relation account set from accounts in the same cluster based on a clustering result.
7. An intelligent PONZH cheat detection terminal, comprising: a memory and a processor;
the memory is used for storing program codes corresponding to an intelligent Pompe fraud detection method of any one of claims 1 to 3;
the processor is configured to execute the program code.
8. A storage medium having stored therein program code corresponding to an intelligent pompe fraud detection method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110510.4A CN112862493B (en) | 2021-01-27 | 2021-01-27 | Intelligent Pompe deception detection method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110110510.4A CN112862493B (en) | 2021-01-27 | 2021-01-27 | Intelligent Pompe deception detection method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112862493A CN112862493A (en) | 2021-05-28 |
| CN112862493B true CN112862493B (en) | 2022-04-15 |
Family
ID=76009502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110110510.4A Active CN112862493B (en) | 2021-01-27 | 2021-01-27 | Intelligent Pompe deception detection method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862493B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548330B (en) * | 2016-10-27 | 2018-03-16 | 上海亿账通区块链科技有限公司 | Transaction verification method and system based on block chain |
| CN108961019B (en) * | 2017-05-17 | 2022-12-16 | 腾讯科技（深圳）有限公司 | User account detection method and device |
| US11354669B2 (en) * | 2018-06-28 | 2022-06-07 | International Business Machines Corporation | Collaborative analytics for fraud detection through a shared public ledger |
| CN109345390A (en) * | 2018-09-25 | 2019-02-15 | 深圳市元征科技股份有限公司 | A kind of intelligence contract access method, system, equipment and computer storage medium |
| CN110599275A (en) * | 2019-09-27 | 2019-12-20 | 腾讯科技（深圳）有限公司 | Data processing method and device based on block chain network and storage medium |
| CN111311416B (en) * | 2020-02-28 | 2024-01-23 | 杭州云象网络技术有限公司 | Block chain money laundering node detection method based on multichannel graph and graph neural network |
| CN111447179A (en) * | 2020-03-03 | 2020-07-24 | 中山大学 | Network representation learning method for phishing and fraud of Ethernet |
| CN111861465A (en) * | 2020-07-21 | 2020-10-30 | 国家计算机网络与信息安全管理中心 | Detection method and device based on intelligent contract, storage medium and electronic device |
-
2021
- 2021-01-27 CN CN202110110510.4A patent/CN112862493B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112862493A (en) | 2021-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108053318B (en) | Method and device for identifying abnormal transactions | |
| CN110070364A (en) | Method and apparatus, storage medium based on the fraud of graph model detection clique | |
| CN106780012A (en) | A kind of internet credit methods and system | |
| CN112669138B (en) | Data processing method and related equipment | |
| CN108876105B (en) | Transaction risk control method and device | |
| CN109345375A (en) | A kind of suspicious money laundering Activity recognition method and device | |
| CN108596760A (en) | loan risk evaluation method and server | |
| KR102005733B1 (en) | Block chain-based person-to-person financial service offering system using credit rating assessment result drawn on online big data analysis | |
| CN116452329A (en) | Abnormal behavior monitoring method and device, electronic equipment and storage medium | |
| CN108197795A (en) | The account recognition methods of malice group, device, terminal and storage medium | |
| CN110942312A (en) | POS machine cash register identification method, system, equipment and storage medium | |
| CN110991650A (en) | Method and device for training card maintenance identification model and identifying card maintenance behavior | |
| CN111311276B (en) | Identification method and device for abnormal user group and readable storage medium | |
| CN112862493B (en) | Intelligent Pompe deception detection method, device, terminal and storage medium | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN110457009B (en) | Method for realizing software security requirement recommendation model based on data analysis | |
| CN110348983B (en) | Transaction information management method and device, electronic equipment and non-transitory storage medium | |
| CN113159778B (en) | Financial fraud detection method and device | |
| CN110570301B (en) | Risk identification method, device, equipment and medium | |
| CN112232962A (en) | Transaction index processing method, device and equipment | |
| CN108846737B (en) | Fraud measurement method | |
| CN115034788A (en) | Transaction risk assessment method and device, electronic equipment and storage medium | |
| CN110245985A (en) | A kind of information processing method and device | |
| CN117078412A (en) | Abnormal funds transaction identification method and device, storage medium and electronic equipment | |
| CN110609829B (en) | Method and system for cleaning and restoring transaction data |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |