Method and system for cryptocurrency fraud detection

Abstract

A method for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling includes: receiving transaction data of multiple fiat-based payment transactions from a first computing system; receiving transaction data of multiple cryptocurrency-based blockchain transactions from a second computing system; receiving node connectivity data of a blockchain network from a third computing system; generating a fraud detection model based on the node connectivity data, including generating a graphical representation of the node connectivity data; receiving transaction data of a new blockchain transaction from a computing device; generating a fraud score for the new transaction using the fraud detection model, the transaction data of the fiat-based transactions, and the transaction data of the cryptocurrency-based transactions; and transmitting the generated fraud score to the computing device.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit and priority of U.S. Patent Application No. 18 / 233,068, filed August 11, 2023. The entire disclosure of the above application is incorporated herein by reference. Technical Field

[0003] This disclosure relates to fraud detection in cryptocurrencies, and more specifically to fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling. Background Technology

[0004] Blockchain was created as a technology for conducting cryptocurrency (also known as blockchain currency) transactions in an anonymous and decentralized system. These characteristics of blockchain can provide several advantages over traditional fiat-based payment transaction systems, such as providing anonymity to participants so that their behavior and spending patterns cannot be tracked, using currencies that are not pegged to fiat currencies and are subject to the volatility of traditional currencies, and being free from any central authority or system and therefore subject to fewer rules and regulations.

[0005] Because transactions on blockchains are typically anonymous and subject to minimal oversight, they fail to benefit from the numerous consumer advantages developed over years in traditional fiat-based payment transactions. For example, consumers using credit cards enjoy significant protections provided by credit card processors, financial institutions, and payment networks against fraud, identity theft, and merchant misconduct, while blockchains offer no protection against any of these situations beyond the protections provided by their decentralized and immutable nature. Some entities operating as exchanges, controlling blockchain wallets on behalf of participants, may offer protection against identity or wallet theft, but they cannot provide protection against fraudulent transactions. While most credit card transactions are settled in fiat currency, some can be settled in cryptocurrency or are associated with cryptocurrency in general. Given the lack of transparency in this area, these transactions often pose a much higher risk for credit card companies. Current fraud scoring methods may be fairly general for a wide range of transactions but do not specifically consider the risk factors associated with cryptocurrencies.

[0006] Therefore, existing systems need to be technically improved to provide fraud protection for new cryptocurrency transactions. Summary of the Invention

[0007] This disclosure provides a description of a system and method for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling. A processing server receives transaction data from traditional fiat-based payment transactions, blockchain transaction data, and node connectivity data of the blockchain network on which new transactions are being initiated. The processing server generates a fraud detection model, as part of which it generates a graphical representation of at least the blockchain network, illustrating the nodes and their connections within the blockchain network. When the processing server receives transaction data for a new blockchain transaction (such as from a potential payer of a transaction), it uses the fraud detection model along with transaction data from past fiat-based payment transactions and blockchain transactions to generate a fraud score for the new blockchain transaction, indicating the likelihood of fraud in the new transaction. The fraud score is provided back to the requester, who can then decide whether to proceed with the new blockchain transaction based on the provided fraud score. In some cases, the disposal of the new transaction can be used to further train the fraud detection model for future transactions.

[0008] The process involves: a receiver on the processing server receiving transaction data for multiple fiat-based payment transactions from a first computing system; a receiver on the processing server receiving transaction data for multiple cryptocurrency-based blockchain transactions from a second computing system; a receiver on the processing server receiving node connectivity data of a blockchain network from a third computing system; a processor on the processing server generating a fraud detection model based at least on the received node connectivity data, wherein generating the fraud detection model includes generating a graphical representation of the received node connectivity data; a receiver on the processing server receiving transaction data for a new blockchain transaction from a computing device; a processor on the processing server using at least the generated fraud detection model, the transaction data for the multiple fiat-based payment transactions, and the transaction data for the multiple cryptocurrency-based blockchain transactions to generate a fraud score for the new blockchain transaction; and a transmitter on the processing server transmitting the generated fraud score to the computing device.

[0009] A system for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling includes: a first computing system; a second computing system; a third computing system; a computing device; a blockchain network; and a processing server, the processing server comprising: a receiver that receives transaction data of multiple fiat-based payment transactions from the first computing system, transaction data of multiple cryptocurrency-based blockchain transactions from the second computing system, and node connectivity data of the blockchain network from the third computing system; a processor that generates a fraud detection model based at least on the received node connectivity data, wherein generating the fraud detection model includes generating a graphical representation of the received node connectivity data; and a transmitter, wherein the receiver of the processing server also receives transaction data of new blockchain transactions from the computing device, the processor of the processing server uses a combination of at least the generated fraud detection model, the transaction data of the multiple fiat-based payment transactions, and the transaction data of the multiple cryptocurrency-based blockchain transactions to generate a fraud score for the new blockchain transaction, and the transmitter of the processing server transmits the generated fraud score to the computing device. Attached Figure Description

[0010] The scope of this disclosure can be best understood from the following detailed description of exemplary embodiments when read in conjunction with the accompanying drawings. The drawings include the following figures:

[0011] Figure 1 This is a block diagram illustrating a high-level system architecture for fraud scoring of cryptocurrency transactions according to an exemplary embodiment.

[0012] Figure 2 The illustration is based on an exemplary embodiment. Figure 1 A block diagram of a processing server in a system used to score cryptocurrency transactions.

[0013] Figure 3 The illustration is based on an exemplary embodiment. Figure 1 The system's processing server generates a flowchart of the fraud detection model's processing for fraud scoring of cryptocurrency transactions.

[0014] Figure 4 This is a graphical representation of a fraud detection model for fraud scoring of cryptocurrency transactions according to an exemplary embodiment.

[0015] Figure 5 The illustration shows an example of a [specific embodiment]. Figure 1 The flowchart shows the process of fraud scoring for cryptocurrency transactions in the system.

[0016] Figure 6 This is a flowchart illustrating an exemplary method for fraud scoring of cryptocurrency transactions according to an exemplary embodiment.

[0017] Figure 7 This is a block diagram illustrating a computer system architecture according to an exemplary embodiment.

[0018] Other areas of application of this disclosure will become clear from the detailed description provided below. It should be understood that the detailed description of exemplary embodiments is for illustrative purposes only and is therefore not intended to necessarily limit the scope of this disclosure. Detailed Implementation

[0019] A system for fraud scoring in cryptocurrency transactions.

[0020] Figure 1 The illustration shows a system 100 that generates and uses fraud scores for cryptocurrency transactions based on multiple datasets and graphical representations.

[0021] System 100 may include a processing server 102. The processing server 102, discussed in more detail below, may be configured to generate a fraud detection model including a graphical representation and to calculate a fraud score for new cryptocurrency transactions on the blockchain using the fraud detection model and data received from multiple sources. System 100 may also include a blockchain associated with a blockchain network 104, on which new blockchain transactions will be added if approved. Blockchain network 104 may include multiple blockchain nodes 106. Each blockchain node 106 may be a computing system, such as those discussed in more detail below. Figure 7 As shown, the computing system is configured to perform functions related to the processing and management of the blockchain, including the generation of blockchain data values, the verification of proposed blockchain transactions, the verification of digital signatures, the generation of new blocks, the verification of new blocks, and the maintenance of copies of the blockchain.

[0022] A blockchain can be a distributed ledger consisting of at least a plurality of blocks. Each block can include at least a block header and one or more data values. Each block header can include at least a timestamp, a block reference value, and a data reference value. The timestamp can be the time when the block header was generated and can be represented using any suitable method (e.g., UNIX timestamp, DateTime, etc.). The block reference value can be a value that references an earlier block in the blockchain (e.g., based on the timestamp). In some embodiments, the block reference value in the block header can be a reference to the block header of the most recently added block preceding the corresponding block. In an exemplary embodiment, the block reference value can be a hash value generated via a hash of the block header of the most recently added block. The data reference value can similarly be a reference to one or more data values ​​stored in the block that includes the block header. In an exemplary embodiment, the data reference value can be a hash value generated via a hash of one or more data values. For example, the block reference value can be the root of a Merkle tree generated using one or more data values.

[0023] Using block reference values ​​and data reference values ​​in the header of each block can make the blockchain immutable. Any attempt to modify a data value requires generating a new data reference value for that block, which in turn requires generating new block reference values ​​for subsequent blocks, and then generating new block reference values ​​in each subsequent block. This must be performed and updated in every individual blockchain node 106 in the blockchain network 104 before a new block is generated and added to the blockchain to make the changes permanent. Computational and communication limitations may make such modifications extremely difficult, if not impossible, thus rendering the blockchain immutable.

[0024] In some embodiments, the blockchain can be used to store information about blockchain transactions between two different blockchain wallets. A blockchain wallet may include a private key for a cryptographic key pair, which is used to generate a digital signature that serves as authorization for the blockchain transaction by the payer, wherein the digital signature can be verified by the blockchain network 104 using the public key of the cryptographic key pair. In some cases, the term "blockchain wallet" may specifically refer to a private key. In other cases, the term "blockchain wallet" may refer to a computing device (e.g., the requesting device 108, etc.) that stores the private key for its use in blockchain transactions. For example, each computing device may have its own private key for a corresponding cryptographic key pair and may each be a blockchain wallet used to transact with the blockchain associated with the blockchain network. The computing device can be any type of device suitable for storing and utilizing a blockchain wallet, such as a desktop computer, laptop computer, notebook computer, tablet computer, cellular phone, smartphone, smartwatch, smart TV, wearable computing device, implantable computing device, etc.

[0025] Where applicable, each blockchain data value stored in the blockchain may correspond to a blockchain transaction or other storage of data. A blockchain transaction may include at least: a digital signature of the sender (e.g., the requesting device 108) of the currency generated using the sender's private key, a blockchain address of the recipient (e.g., participating device 110) of the currency generated using the recipient's public key, and the amount of blockchain currency transferred or other data being stored. In some blockchain transactions, the transaction may also include one or more blockchain addresses of the sender currently storing the blockchain currency (e.g., digital signatures proving they can access such currency), and an address generated using the sender's public key for any changes retained by the sender. Addresses to which cryptocurrency that can be used in future transactions has been sent are called "output" addresses because each address was previously used to capture the output of previous blockchain transactions, and are also called "unspent transactions" because currency was sent to that address in a previous transaction but has not yet been used. In some cases, a blockchain transaction may also include the sender's public key for entities to use when verifying the transaction. For conventional processing of blockchain transactions, such data may be provided by either the sender or the recipient to blockchain node 106 in blockchain network 104. A node can verify a digital signature using the public key in the sender's wallet's key pair, and also verify the sender's access to the funds (e.g., an unspent transaction has not yet been spent and sent to the address associated with that sender's wallet). This process is called "confirmation" of the transaction, and the blockchain transaction is then included in a new block. In conventional blockchain implementations, a new block can be verified by the other blockchain nodes 106 in the blockchain network 104 before being added to the blockchain and distributed to all blockchain nodes 106 in the blockchain network 104. Where the blockchain data value may not be associated with a blockchain transaction, but rather with the storage of other types of data, the blockchain data value may still include or otherwise involve the verification of the digital signature.

[0026] As discussed in this article, blockchain currency (also known as cryptocurrency) can refer to any asset that can be stored on a blockchain and transferred through blockchain transactions. Blockchain currency can include any cryptocurrency, stablecoin (e.g., blockchain currency pegged to fiat currency or other assets), non-fungible tokens, digital tokens, fiat currency stored on a blockchain, etc.

[0027] In system 100, a user of requesting device 108 may be interested in participating in a new blockchain transaction to be added to the blockchain associated with blockchain network 104. Requesting device 108 may participate in the new blockchain transaction as either a payer or a payee, and may also participate in the new blockchain transaction with participating device 110, which, where applicable, may be a sender of cryptocurrency to or a receiver of cryptocurrency from requesting device 108. To initiate a new blockchain transaction, requesting device 108 may receive the necessary data for the new blockchain transaction. If requesting device 108 is a payer, this data may include a destination blockchain address (e.g., generated by the public key of participating device 110 and electronically transmitted to requesting device 108 using a suitable communication network and method) and the cryptocurrency amount; or if requesting device 108 is a payee, this data includes a digital signature and one or more unspent transaction outputs from requesting device 108, the cryptocurrency amount, and a destination address generated by the public key of requesting device 108's blockchain wallet. Traditionally, the requesting device 108 can use conventional methods to electronically transmit the transaction data of the new blockchain transaction to the blockchain node 106 in the blockchain network 104 for verification, confirmation, and addition to the blockchain.

[0028] In system 100, a user of requesting device 108 may be interested in generating a fraud score for a new blockchain transaction before or as part of its submission to blockchain node 106. For example, a user may be participating in a blockchain transaction with participating device 110 for the first time and may be interested in using the fraud score to measure the likelihood that participating device 110 is genuine and not involved in fraud. To receive such a fraud score, requesting device 108 may electronically transmit a scoring request to processing server 102 using suitable communication networks and methods (such as via an application, webpage, etc., associated with processing server 102). In some cases, requesting device 108 may submit a new blockchain transaction to blockchain node 106 and, as part of the submission, request a fraud score, where blockchain node 106 may electronically transmit the new blockchain transaction or its data to processing server 102 for scoring using suitable communication networks and methods.

[0029] To generate a fraud score for a new blockchain transaction, processing server 102 may utilize a fraud detection model, which may include a graphical representation of at least a portion of the blockchain network 104 (including at least blockchain nodes 106 to which the new blockchain transaction has been submitted or will be submitted). Processing server 102 may receive data from multiple different data sources for generating the fraud detection model and / or fraud score. As a data source, processing server 102 may receive transaction data for multiple payment transactions using fiat currency (such as traditional electronic payment transactions using credit cards, debit cards, etc.), which may be received from fiat currency transaction data provider 112. Fiat currency transaction data provider 112 may be any entity or system that collects transaction data for fiat currency-based payment transactions, such as financial institutions, payment networks, transaction processors, clearinghouses, etc. Fiat currency transaction data provider 112 may collect transaction data and provide it to processing server 102 using appropriate communication networks and methods. In some cases, fiat currency transaction data provider 112 may also provide data associated with an individual consumer with the consumer's permission. If the consumer approves, this data may include personally identifiable information, such as name, address, email address, transaction account, etc. Transaction data for fiat currency-based payment transactions may include transaction amount, merchant, financial institution, time and / or date, transaction frequency, geographic location, currency, point-of-sale identifier, fraud determination, etc. In some cases, transaction data may be separated by individual transactions. In other cases, processing server 102 may receive aggregated transaction data. With the approval of a consumer associated with the requesting device 108, the transaction data may include data related to that consumer's personal payment transactions.

[0030] As another data source, processing server 102 can receive transaction data from multiple cryptocurrency blockchain transactions from blockchain data provider 116. Blockchain data provider 116 can be any entity or system that collects transaction data for cryptocurrency blockchain transactions using at least the blockchains associated with blockchain network 104. In some instances, blockchain data provider 116 can be blockchain node 106 within blockchain network 104. In some cases, blockchain data provider 116 can collect transaction data for blockchain transactions targeting different blockchains, such as when blockchain node 106 in blockchain network 104 operates as a node in an additional blockchain network, or when blockchain network 104 can operate multiple blockchains. Blockchain data provider 116 can collect transaction data and provide it to processing server 102 using appropriate communication networks and methods. In some cases, blockchain data provider 116 can also provide data associated with an individual participant with their permission. If the participant approves, this data may include personally identifiable information, such as public keys, telephone numbers, email addresses, device identifiers of their computing devices, etc. Transaction data for blockchain transactions may include transaction amount, blockchain node, time and / or date, transaction frequency, geographical location, fraud determination, etc. In some cases, transaction data may be separated by individual transactions. In other cases, processing server 102 may receive aggregated transaction data. With the approval of a participant associated with the requesting device 108, transaction data may include data related to that participant's individual blockchain transactions.

[0031] As a third data source, processing server 102 can receive node connectivity data of blockchain network 104 from node data provider 114. Node data provider 114 can be any entity or system that collects connectivity data at least for blockchain network 104. In some instances, node data provider 114 can be blockchain node 106 in blockchain network 104. In some embodiments, node data provider 114 and blockchain data provider 116 can be the same entity and / or computing system. In some cases, node data provider 114 can collect connectivity data for additional blockchain networks 104, such as when blockchain node 106 in blockchain network 104 operates as a node in an additional blockchain network. Node data provider 114 can collect node connectivity data and provide transaction data to processing server 102 using appropriate communication networks and methods. Node connectivity data can include data about blockchain nodes 106 in blockchain network 104 and connections between nodes. In some embodiments, node connectivity data can also include information about the transaction history of each blockchain node 106. In other embodiments, information about the transaction history of each blockchain node may be included in transaction data received from blockchain data provider 116, which may be cross-referenced with node connectivity data received from node data provider 114.

[0032] Once processing server 102 has received data from multiple data sources, it can generate a fraud detection model. The fraud detection model can be generated using at least the node connectivity data of blockchain network 104. When the model is fed applicable transaction data for a new blockchain transaction, it can be used to determine the likelihood of fraud in the new blockchain transaction. In an exemplary embodiment, the fraud detection model may include a graphical representation of the blockchain nodes 106 in blockchain network 104 and their connections, such as... Figure 4 The graphical representation 400 is illustrated in the figure and discussed in more detail below. The graphical representation may include a representation of each blockchain node 106 and the connections of each blockchain node 106 to other blockchain nodes 106 in the blockchain network 104. This representation can be used in fraud detection models, where a blockchain node 106 connected to a large number of other blockchain nodes 106 (while these other nodes are not connected to other blockchain nodes 106) can indicate fraud, or a blockchain node 106 connected to other blockchain nodes 106 with a history of fraudulent transactions can indicate fraud.

[0033] In some cases, the fraud detection model may also utilize transaction data from fiat-based payment transactions and cryptocurrency-based blockchain transactions. In such cases, the transaction data may be utilized separately from the graphical representation, such as through one or more algorithms, which, when combined with the graphical representation, can be used to generate a fraud score. In some embodiments, the processing server 102 may use artificial intelligence and / or machine learning in generating the fraud detection model, which can be trained using transaction data and node connectivity data, as well as a history of past blockchain transactions and fiat-based payment transactions as treated as fraud or non-fraudulent. In some cases, the fraud detection model may also use clustering and / or other modeling techniques, in addition to the above, to calculate the fraud score, where clustering may include clusters of blockchain nodes 106, blockchain transactions, fiat-based payment transactions, etc. In embodiments where the processing server 102 may receive transaction data or other data relating to the requesting device 108 or its associated participants, the processing server 102 may generate a fraud detection model suitable for the requesting device 108 or its associated participants.

[0034] Once processing server 102 has generated its fraud detection model and received transaction data for a new blockchain transaction from requesting device 108 or blockchain node 106, processing server 102 can generate a fraud score for the new blockchain transaction by applying the transaction data to the fraud detection model. The transaction data for the new blockchain transaction may include the transaction amount, one or more unspent transaction outputs associated with the payer of the blockchain transaction, the destination address of the payee of the blockchain transaction, the identification information of blockchain node 106 used to confirm the new blockchain transaction and add it to the blockchain, and any other suitable data for performing the functions discussed herein, such as the identification information of the user of requesting device 108 and / or the user of participating device 110 (if approved by the respective user). Processing server 102 can apply the transaction data to the fraud detection model and generate a fraud score for the new blockchain transaction, which indicates the likelihood of fraud in the new blockchain transaction. If the requesting device 108 or participating device 110 has been involved in past fraudulent blockchain transactions, if blockchain node 106 has been involved in past fraudulent blockchain transactions, if blockchain node 106 is in a cluster indicating fraudulent activity in the graphical representation, if the transaction frequency of the requesting device 108, participating device 110, or blockchain node 106 is unusually low or high, if a user associated with the requesting device 108 or participating device 110 has been involved in past fraudulent transactions, if the transaction amount of the new blockchain transaction is significantly greater than the average transaction amount of past blockchain or fiat-based payment transactions of the requesting device 108 or participating device 110, or if the geographical location of the requesting device 108 or participating device 110 in the new blockchain transaction is different from the corresponding device's past geographical location, then the fraud score can be increased (e.g., indicating a higher probability of fraud).

[0035] Processing server 102 can generate a fraud score for new blockchain transactions and provide the fraud score in response to a score request. In some cases, the fraud score can be provided back to the requesting device 108 (e.g., directly by processing server 102 or via blockchain node 106 used by the requesting device 108). In such cases, the requesting device 108 can prompt its user to approve or reject the new blockchain transaction based on the fraud score. In some such cases, the requesting device 108 can be configured to automatically approve or reject new blockchain transactions based on the fraud score (e.g., based on user instructions), such as using a user-provided threshold. The requesting device 108 can communicate the approval or rejection of the blockchain transaction to blockchain node 106. If the transaction is rejected, blockchain node 106 can discard the transaction data of the new blockchain transaction and take no further action. If the transaction is approved, blockchain node 106 can confirm the blockchain transaction using conventional methods and add the blockchain transaction to a new block in the blockchain.

[0036] In some cases, a fraud score can be provided by processing server 102 to blockchain node 106, where blockchain node 106 can be configured to approve or reject blockchain transactions on behalf of requesting device 108. In such cases, blockchain node 106 can automatically approve or reject new blockchain transactions based on the received fraud score and a predetermined threshold, which can be set by blockchain node 106 or by requesting device 108, either by the requesting device 108 or by the requesting device 108 along with the new blockchain transaction.

[0037] In some embodiments, a fraud score may be provided by processing server 102 to another system for approving or rejecting a new blockchain transaction. For example, system 100 may include a third-party system 118, which may be any system or entity participating in a new blockchain transaction on behalf of or otherwise associated with the requesting device 108. For example, third-party system 118 may be a financial institution, such as an issuing bank, which issues a transaction account (e.g., a blockchain wallet, fiat currency payment account, etc.) to the requesting device 108 to fund the new blockchain transaction. Processing server 102 may transmit the fraud score to third-party system 118, which may use the fraud score to determine whether to approve or reject the new blockchain transaction. In some cases, third-party system 118 may determine whether to approve or reject the new blockchain transaction based on the fraud score itself (e.g., compared to a threshold). In other cases, third-party system 118 may combine the fraud score with other available data when making a determination to approve or reject the new blockchain transaction. The third-party system 118 can directly transmit the approval or rejection to the blockchain node 106, the requesting device 108, or the processing server 102 for appropriate processing.

[0038] In some embodiments, processing server 102 may update the fraud detection model based on the disposal of the new blockchain transaction. For example, if the user who issued the request, device 108, approves the new blockchain transaction, processing server 102 may modify the fraud detection model so that future transactions similar to the new blockchain transaction have a lower fraud score due to a lower probability of fraud. In another example, if the requesting device 108 rejects the new blockchain transaction, processing server 102 may modify the fraud detection model so that future transactions similar to the new blockchain transaction have a higher fraud score due to a higher probability of fraud. In some cases, the requesting device 108 may provide feedback on the approval or rejection of the new blockchain transaction, which may be used to modify the fraud detection model, such as the reasons given by the user for approving or rejecting the new blockchain transaction. In some cases, processing server 102 may use the disposal of the new blockchain transaction based on the outcome of the new blockchain transaction itself rather than the user's approval or rejection of the new blockchain transaction. In such cases, if a blockchain transaction occurs without any indication of fraud, the processing server 102 can use the transaction data of the new blockchain transaction as a positive result to modify the fraud detection model. Conversely, if the new blockchain transaction is later found to involve fraud, the processing server 102 can use the transaction data of the new blockchain transaction as a negative result to modify the fraud detection model. In the latter case, the fraud detection model can be updated based on the source of the fraud in the new blockchain transaction (e.g., blockchain node 106, the requesting device 108, participating device 110, etc.).

[0039] In some embodiments, processing server 102 may be configured to update the fraud detection model when new data is received. For example, processing server 102 may receive new transaction data or new node connectivity data and thereby update the fraud detection model. In some instances, processing server 102 may update the fraud detection model each time new data is received. In other instances, processing server 102 may update the fraud detection at periodic intervals (e.g., hourly, daily, weekly, etc.). In some embodiments, fiat currency transaction data provider 112, node data provider 114, and / or blockchain data provider 116 may provide updated data to processing server 102 at any time when updated data is available or at periodic intervals.

[0040] The methods and systems discussed in this paper provide fraud scoring for cryptocurrency transactions using multiple data sources and graphical representations to assist in the approval or rejection of new blockchain transactions. By using data from multiple sources, including not only blockchain transaction data, more comprehensive and accurate fraud scores can be obtained, such as in cases where a participant may have a long history of successful fiat-based transactions but is new to the blockchain. Furthermore, the use of graphical representations can provide more accurate fraud scores, particularly relevant to blockchain nodes, where fraudulent activity can be indicated solely through graphical representation. Therefore, the methods and systems discussed in this paper offer significant improvements over existing systems in fraud scoring of blockchain transactions, which can benefit all participants in the blockchain, including the blockchain network 104 itself, by blocking and preventing transactions carried out by fraudulent or compromised blockchain nodes 106.

[0041] Processing server

[0042] Figure 2 The diagram shows Figure 1 An embodiment of the processing server 102 in system 100. It will be clear to those skilled in the art that... Figure 2 The embodiment of the processing server 102 illustrated herein is provided for illustrative purposes only and does not exhaustively represent all possible configurations of the processing server 102 suitable for performing the functions discussed herein. For example, Figure 7 The computer system 700 illustrated in the diagram and discussed in more detail below can be a suitable configuration for processing server 102. In some cases, other components of system 100, such as blockchain node 106, requesting device 108, participating device 110, fiat currency transaction data provider 112, node data provider 114, and blockchain data provider 116, may include... Figure 2 The components are illustrated in the diagram and discussed below.

[0043] Processing server 102 may include receiving device 202. Receiving device 202 may be configured to receive data via one or more networks through one or more network protocols. In some instances, receiving device 202 may be configured to receive data from blockchain node 106, requesting device 108, participating device 110, fiat currency transaction data provider 112, node data provider 114, blockchain data provider 116, and other systems and entities via one or more communication methods (such as radio frequency, local area network, wireless local area network, cellular communication network, Bluetooth, Internet, etc.). In some embodiments, receiving device 202 may include multiple devices, such as different receiving devices for receiving data via different networks, such as a first receiving device for receiving data via a local area network and a second receiving device for receiving data via the Internet. Receiving device 202 may receive data signals transmitted electronically, wherein data may be superimposed or otherwise encoded on the data signals, and receive data signals via receiving device 202 to decode, parse, read, or otherwise obtain them. In some cases, receiving device 202 may include a parsing module for parsing the received data signals to obtain the data superimposed thereon. For example, receiving device 202 may include a parser program configured to receive data signals and transform the received data signals into usable inputs for functions performed by a processing device to execute the methods and systems described herein.

[0044] The receiving device 202 can be configured to receive data signals electronically transmitted by the blockchain node 106. These data signals can be overlaid with or otherwise encoded using blockchain data, new blockchain transactions, rating requests, transaction data of past cryptocurrency blockchain transactions, node connectivity data of the blockchain network 104, and processing notifications of past blockchain transactions. The receiving device 202 can also be configured to receive data signals electronically transmitted by the requesting device 108 and participating device 110. These data signals can be overlaid with or otherwise encoded using new blockchain transactions, rating requests, processing notifications, personally identifiable information approvals, and transaction history. The receiving device can also be configured to receive data signals transmitted electronically by other computing systems, including fiat currency transaction data provider 112, node data provider 114, and blockchain data provider 116. These data signals can be overlaid with transaction data, node connectivity data, and other data used to generate fraud detection models and fraud scores for generating new blockchain transactions (as discussed herein), or otherwise encoded with transaction data, node connectivity data, and other data used to generate fraud detection models and fraud scores for generating new blockchain transactions (as discussed herein).

[0045] Processing server 102 may also include a communication module 204. Communication module 204 may be configured to transfer data between modules, engines, databases, memory, and other components of processing server 102 for performing the functions discussed herein. Communication module 204 may include one or more communication types and utilize various communication methods for communication within the computing device. For example, communication module 204 may include a bus, a pin connector, wires, etc. In some embodiments, communication module 204 may also be configured to communicate between internal components of processing server 102 and external components of processing server 102, such as externally connected databases, display devices, input devices, etc. Processing server 102 may also include a processing device. The processing device may be configured to perform the functions of processing server 102 discussed herein, as will be apparent to those skilled in the art. In some embodiments, the processing device may include and / or consist of multiple engines and / or modules specifically configured to perform one or more functions of the processing device, such as query module 216, generation module 218, scoring module 220, etc. As used herein, the term "module" can be software or hardware specifically programmed to receive input, perform one or more processes using that input, and provide output. Based on this disclosure, those skilled in the art will understand the inputs, outputs, and processing performed by various modules.

[0046] The processing server 102 may also include transaction data 206, which may be stored in the storage 214 of the processing server 102 or stored in or accessible from a separate area within the processing server 102. Transaction data 206 may include data associated with one or more fiat-based payment transactions, one or more cryptocurrency-based blockchain transactions, personal transaction accounts, personal blockchain wallets, individual consumers of payment transactions, or participants in blockchain transactions. Transaction data 206 may include transaction amount, transaction time and / or date, transaction frequency, merchant data, participant data, fraud score, fraud determination, fraud handling, and other data as discussed herein.

[0047] Processing server 102 may also include blockchain data 210, which may be stored in storage 214 of processing server 102 or in a separate area within processing server 102 or accessible thereto. Blockchain data 210 may include a blockchain, which may include multiple blocks and is associated with blockchain network 104 and the core blockchain. In some cases, blockchain data 210 may also include any other data associated with the blockchain and its management and execution, such as block generation algorithms, digital signature generation and verification algorithms, communication data for blockchain nodes 106, smart contracts, cryptographic keys, etc. Blockchain data 210 may also include data used by processing server 102 for actions associated with the blockchain, such as cryptographic key pairs for blockchain wallets, public keys for generating destination addresses or verifying digital signatures, transaction history, cryptocurrency amounts, etc.

[0048] Processing server 102 may also include memory 214. Memory 214 may be configured to store data for use by processing server 102 in performing the functions discussed herein, such as public and private keys, symmetric keys, etc. Memory 214 may be configured to store data using suitable data formatting methods and patterns, and may be any suitable type of memory, such as read-only memory, random access memory, etc. Memory 214 may include, for example, cryptographic keys and algorithms, communication protocols and standards, data formatting standards and protocols, program code for modules and applications for processing devices, and other data that may be suitable for use by processing server 102 in performing the functions disclosed herein, as will be apparent to those skilled in the art. In some embodiments, memory 214 may consist of or otherwise include a relational database that utilizes a structured query language for storing, identifying, modifying, updating, accessing, etc., structured datasets stored therein. The memory 214 can be configured to store, for example, cryptographic keys, cryptographic key pairs, cryptographic algorithms, encryption algorithms, communication information, data format rules, network identifiers, fraud scoring rules, artificial intelligence data, machine learning data, artificial intelligence models, fraud detection models, etc.

[0049] Processing server 102 may include query module 216. Query module 216 may be configured to perform queries against a database to identify information. Query module 216 may receive one or more data values ​​or query strings and may execute the query strings based on an indicated database (such as memory 214 of processing server 102) to identify information stored therein. Query module 216 may then output the identified information to an appropriate engine or module of processing server 102 as needed. For example, query module 216 may execute a query on memory 214 to identify a fraud detection model used to generate fraud scores for new blockchain transactions.

[0050] Processing server 102 may also include a generation module 218. Generation module 218 may be configured to generate data for use by processing server 102 when performing the functions discussed herein. Generation module 218 may receive instructions as input, generate data based on the instructions, and output the generated data to one or more modules of processing server 102. For example, generation module 218 may be configured to generate a fraud detection model, which may include a graphical representation generated by generation module 218 based on node connectivity data and any other data discussed herein. Generation module 218 may also be configured to update the generated graphical representation and / or fraud detection model with new or updated transaction data, node connectivity data, etc.

[0051] The processing server 102 may also include a scoring module 220. The scoring module 220 can be configured to score the likelihood of fraud in new blockchain transactions against the processing server 102, as part of the functionality discussed herein. The scoring module 220 can receive a request to score a new blockchain transaction as input, the request may also include transaction data of the new blockchain transaction for determining the score, can score the new blockchain transaction upon request, and can output the score to another module or engine of the processing server 102.

[0052] The processing server 102 may also include a transmission device 222. The transmission device 222 may be configured to transmit data over one or more networks via one or more network protocols. In some instances, the transmission device 222 may be configured to transmit data to blockchain node 106, requesting device 108, participating device 110, fiat currency transaction data provider 112, node data provider 114, blockchain data provider 116, and other entities via one or more communication methods (LAN, wireless LAN, cellular communication, Bluetooth, radio frequency, Internet, etc.). In some embodiments, the transmission device 222 may include multiple devices, such as different transmission devices for transmitting data over different networks, such as a first transmission device for transmitting data over a LAN and a second transmission device for transmitting data over the Internet. The transmission device 222 may electronically transmit data signals having overlaid data that can be parsed by a receiving computing device. In some cases, the transmission device 222 may include one or more modules for overlaying, encoding, or otherwise formatting data into data signals suitable for transmission.

[0053] The transmission device 222 can be configured to electronically transmit data signals to the blockchain node 106. These data signals can be overlaid with or otherwise encoded using blockchain data requests, node connectivity requests, fraud score determinations, fraud handling requests, etc. The transmission device 222 can also be configured to electronically transmit data signals to the requesting device 108 and / or participating device 110. These data signals can be overlaid with or otherwise encoded using fraud score determinations, transaction data requests, personally identifiable information approval requests, blockchain data requests, etc. The transmission device 222 can also be configured to electronically transmit data signals to fiat currency transaction data providers 112, node data providers 114, and / or blockchain data providers 116. These data signals can be overlaid with or otherwise encoded using data requests for updated transaction data and / or node connectivity data.

[0054] Processing for generating fraud detection models

[0055] Figure 3 The diagram illustrates the process of... Figure 1 The processing server 102 in system 100 performs processing 300, which generates a fraud detection model using graphical representations and data from multiple data sources for fraud scoring of cryptocurrency transactions.

[0056] Processing 300 can commence, and in step 302, the receiving device 202 of processing server 102 can receive transaction data for multiple fiat-based payment transactions from fiat-currency transaction data provider 112. In some cases, the transaction data can be broken down into individual payment transactions. In other cases, the transaction data can be aggregated. In some instances, the transaction data may include additional data associated with individual transaction accounts, such as where the consumer associated with each transaction account has explicitly approved its use for fraud scoring. The query module 216 of processing server 102 can execute queries to insert the received transaction data into the transaction data 206 of processing server 102.

[0057] In step 304, the receiving device 202 of the processing server 102 may receive transaction data of multiple cryptocurrency-based blockchain transactions from the blockchain data provider 116. In some cases, the transaction data may be broken down into individual blockchain transactions. In other cases, the transaction data may be aggregated. In some instances, the transaction data may include additional data associated with individual blockchain wallets, such as where the user associated with each blockchain wallet has explicitly approved its use for fraud scoring. The query module 216 of the processing server 102 may execute a query to insert the received transaction data into the transaction data 206 of the processing server 102.

[0058] In step 306, the receiving device 202 of the processing server 102 may receive node connectivity data of the blockchain network 104 from the node data provider 114. The node connectivity data may include data about one or more blockchain nodes 106 in the blockchain network 104 and the communication paths between the blockchain nodes 106. The query module 216 of the processing server 102 may execute a query to insert the received node connectivity data into the blockchain data 210 or memory 214 of the processing server 102.

[0059] In step 308, the generation module 218 of the processing server 102 can generate a fraud detection model. The fraud detection model may include at least a graphical representation of the blockchain nodes 106 in the blockchain network 104 generated based on received node connectivity data. The fraud detection model may be based on the graphical representation and transaction data of received fiat-based payment transactions and cryptocurrency blockchain transactions. In some cases, the graphical representation may utilize clustering of the blockchain nodes 106. A fraud detection model can be generated such that when transaction data of a new blockchain transaction is applied, a fraud score indicating the likelihood of fraud in the new blockchain transaction can be generated based on a combination of the transaction data and the graphical representation of the nodes in the blockchain network 104. In some embodiments, the generation module 218 of the processing server 102 may use artificial intelligence and / or machine learning when generating the fraud detection model. In some cases, the processing server 102 may use one or more specific artificial intelligence models to generate the fraud detection model. In some instances, weighting may be used on the transaction data and / or node connectivity data when generating the fraud detection model. The processing server 102 can then be prepared to use the generated fraud detection model to score future blockchain transactions for fraud, such as... Figure 5 As discussed in the diagram and in more detail below.

[0060] Graphical representation of node connectivity

[0061] Figure 4The diagram illustrates a graphical representation 400 of the node connectivity in a blockchain network 104 for use by the processing server 102 in generating fraud detection models and scoring new blockchain transactions for fraud. As will be clear to those skilled in the art... Figure 4 The graphic representation 400 in the diagram is merely illustrative, and the blockchain network 104 may include significantly more or fewer blockchain nodes 106, which may have significantly more or fewer connections to other blockchain nodes 106.

[0062] The graphical representation 400 includes multiple blockchain nodes 106 in the blockchain network 104 as representations of nodes 402. The graphical representation 400 also includes a diagram of a connection 404 between nodes 402, representing a communication path between two blockchain nodes 106 in the blockchain network 104. The communication path can be a persistent communication channel established between the two blockchain nodes 106, or it can indicate past communication between the two blockchain nodes 106, such as past confirmation requests or response messages. In some cases, the processing server 102 may use a time cutoff point when determining whether to diagram a connection 404 for two nodes 402 in the graphical representation 400. For example, a connection 404 may be diagrammed if two nodes 402 have exchanged communication within a predetermined time period (e.g., the most recent 24 hours).

[0063] As shown in the figure, some nodes 402 may have only a single connection to another node 402, while other nodes 402 may have connections to several other nodes 402. A node 402 with only a single connection may be a new blockchain node 106 that has not yet established a communication channel with an attached blockchain node 106, but it may also indicate a blockchain node 106 involved in fraud. The fraud detection model can influence the fraud score of a new blockchain transaction based on how the blockchain nodes 106 that submit new blockchain transactions to the requesting device 108 or receive new blockchain transactions from the processing server 102 are displayed in the graphical representation, where the number of connections 404 to the associated node 402 and the position of the node 402 in the representation can positively or negatively affect the fraud score.

[0064] In an exemplary embodiment, the graphical representation 400 may utilize clustering. Clustering may include grouping one or more nodes 402 into clusters 406 based on shared connections 404, geographic location, communication frequency, and other suitable data. In the illustrated example, the generation module 218 may generate four clusters 406, illustrated as clusters 406a, 406b, 406c, and 406d. The fraud detection module may utilize clusters 406 when determining fraud scores, wherein attributes of clusters 406 may positively or negatively influence fraud scores, and wherein attributes of nodes 402 in clusters 406 may positively or negatively influence fraud scores of other nodes 402 in the same cluster 406.

[0065] In the illustrated example, cluster 406b can be associated with the lowest fraud probability due to the number of nodes 402 in cluster 406b and the number of connections 404 between each node 402. Cluster 406b includes ten distinct nodes 402, and each node 402 includes three or more connections 404 with other nodes 402 in cluster 406, which can represent a low fraud probability because it is difficult to transmit fraudulent transactions through this cluster 406. Clusters 406a and 406d can represent a higher fraud probability than cluster 406b because they have fewer nodes 402 and fewer connections 404, but because each node 402 has multiple connections 404 and each cluster 406 has connections 404 with multiple additional clusters 406, the fraud probability can be below the threshold indicating fraud.

[0066] In the illustrated example, cluster 406c can indicate the highest probability of fraud. Because cluster 406c comprises several nodes 402 that share connections 404 only with a single central node 402 within cluster 406c, and where the central node 402 in cluster 406c has the fewest number of connections 404 with other nodes 402 outside cluster 406c, it can indicate a high probability of fraud. This could indicate that a malicious actor is attempting to transmit fraudulent transactions onto the blockchain via the central node in cluster 406c, which obtains confirmation from compromised blockchain node 106 (which is another node 402 in cluster 406c) and then relays that confirmation to other nodes 402 in cluster 406.

[0067] Fraud scoring for cryptocurrency blockchain transactions

[0068] Figure 5 The illustration shows 500 methods for fraud scoring of cryptocurrency blockchain transactions using fraud detection models and graphical representations, such as... Figure 1 The use of system 100 Figure 4 The graphic representation of 400 in Figure 3 The fraud detection model generated in the 300 processing steps.

[0069] In step 502, the requesting device 108 may receive data from the new blockchain transaction, which may include data from the recipient (e.g., participating device 110) such as a destination address, and data input by the user of the requesting device 108 such as transaction amount and unspent transaction output. In step 504, the requesting device 108 may submit a rating request for the new blockchain transaction to the processing server 102 using a suitable communication network and method. In some cases, the rating request may be submitted by the requesting device 108 to the processing server 102 via blockchain node 106, which, if approved, adds the new blockchain transaction to the blockchain. In other cases, the rating request may be submitted directly from the requesting device 108 to the processing server 102. In such cases, the rating request may also include an identifier associated with the blockchain node 106, which, if approved, is used by the requesting device 108 to add the new blockchain transaction to the blockchain.

[0070] In step 506, the receiving device 202 of the processing server 102 may receive a scoring request from the requesting device 108. In step 508, the processing server 102 may identify all applicable data for fraud scoring of the new blockchain transaction. Applicable data may be an applicable fraud detection model, which may be based on transaction data of the new blockchain transaction, such as in cases where the fraud detection model may be based on changes in transaction amount or a fraud detection model specifically generated for the requesting device 108. Applicable data may also include transaction data relating to fiat-based payment transactions involving users associated with the requesting device 108, and transaction data relating to cryptocurrency blockchain transactions involving the requesting device 108 (where the user has provided approval for the use of such data).

[0071] In step 510, the scoring module 220 of the processing server 102 can apply the received new blockchain transaction data and the identified applicable data to the identified fraud detection model to generate a fraud score for the new blockchain transaction. The fraud score can indicate the likelihood that the new blockchain transaction involves fraud, which can be indicated as being committed by the requesting device 108, participating device 110, or blockchain node 106. In step 512, the transmission device 222 of the processing server 102 can electronically transmit the generated fraud score to the requesting device 108 using a suitable communication network and method. Where applicable, the generated fraud score can be transmitted directly from the processing server 102 to the requesting device 108, or via the blockchain node 106.

[0072] In step 514, the requesting device 108 can receive a fraud score generated for the new blockchain transaction from the processing server 102. In step 516, the requesting device 108 can display the received fraud score to its user and prompt the user to approve the new blockchain transaction. If the fraud score is suitable for the user, the user can approve the new blockchain transaction, which allows the requesting device 108 to submit the new blockchain transaction to the identified blockchain node 106 in step 518 to add it to the blockchain associated with blockchain network 104. In step 520, the blockchain node 106 can receive the new blockchain transaction from the requesting device 108. In step 522, the blockchain node 106 can confirm the new blockchain transaction and add it to the blockchain using conventional methods.

[0073] In some embodiments, the process may further include steps 524 and 526. In step 524, the receiving device 202 of the processing server 102 may receive updated blockchain transaction data from blockchain node 106, blockchain data provider 116, or by identifying new blockchain data stored in the blockchain. The updated blockchain transaction data may include at least a new blockchain transaction that has been successfully approved and added to the blockchain by the requesting device 108. In step 526, the generation module 218 of the processing server 102 may update the graphical representation and fraud detection model based on the updated blockchain transaction data. For example, because a new blockchain transaction has been approved and successfully processed, blockchain node 106 in the graphical representation and the cluster 406 including blockchain node 106 may have a lower probability of fraud, and the fraud detection model may be updated so that the future fraud score involving blockchain node 106 and its cluster can generate a lower fraud score.

[0074] Exemplary method for fraud scoring of blockchain transactions

[0075] Figure 6 The illustration shows a method for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling.

[0076] In step 602, the receiver (e.g., receiving device 202) of the processing server (e.g., processing server 102) may receive transaction data for multiple fiat-based payment transactions from the first computing system (e.g., fiat currency transaction data provider 112). In step 604, the receiver of the processing server may receive transaction data for multiple cryptocurrency-based blockchain transactions from the second computing system (e.g., blockchain data provider 116). In step 606, node connectivity data of the blockchain network (e.g., blockchain network 104) may be received from the third computing system (e.g., node data provider 114).

[0077] In step 608, a fraud detection model may be generated by the processor of the processing server (e.g., generation module 218) based at least on the received node connectivity data, wherein generating the fraud detection model includes generating a graphical representation (e.g., graphical representation 400) of the received node connectivity data. In step 610, transaction data of the new blockchain transaction may be received by the receiver of the processing server from a computing device (e.g., the requesting device 108). In step 612, a fraud score may be generated for the new blockchain transaction by the processor of the processing server (e.g., scoring module 220) using at least the generated fraud detection model, transaction data of multiple fiat-based payment transactions, and transaction data of multiple cryptocurrency-based blockchain transactions. In step 614, the generated fraud score may be transmitted to the computing device by the transmitter of the processing server (e.g., transmission device 222).

[0078] In one embodiment, the graphical representation may include at least a visual representation of each of a plurality of blockchain nodes in a blockchain network and connections between one or more of the blockchain nodes. In a further embodiment, the visual representation of each of the plurality of blockchain nodes included in the graphical representation may indicate the likelihood of the corresponding blockchain node being involved in fraudulent activity based on transaction data from multiple received cryptocurrency-based blockchain transactions. In some embodiments, if transaction data from a new blockchain transaction identifies a blockchain node in the blockchain network with a high probability of fraud based on node connectivity data of the blockchain network, then a fraud score may indicate a higher probability of fraud. In a further embodiment, a higher probability of fraud based on node connectivity data may be indicated by the blockchain node or an auxiliary blockchain node directly connected to the blockchain node having a number of connected nodes in the blockchain network greater than a predetermined threshold without additional connections.

[0079] In one embodiment, the fraud detection model can be generated using artificial intelligence. In some embodiments, method 600 may further include modifying the generated fraud detection model by a processor of a processing server based on the generated fraud score. In a further embodiment, method 600 may even include receiving a message instructing the disposal of a new blockchain transaction by a receiver of the processing server, wherein the modified generated fraud detection model may also be based on the disposal of the indicated new blockchain transaction.

[0080] Computer System Architecture

[0081] Figure 7A computer system 700 is illustrated, wherein embodiments of the present disclosure or portions thereof can be implemented as computer-readable code. For example, a processing server 102, a blockchain node 106, a requesting device 108, a participating device 110, a fiat currency transaction data provider 112, a node data provider 114, and a blockchain data provider 116 may be implemented in computer system 700 using hardware, a non-transitory computer-readable medium on which instructions are stored, or a combination thereof, and may be implemented in one or more computer systems or other processing systems. Hardware may be implemented for implementation... Figure 3 , Figure 5 and Figure 6 The modules and components of the method.

[0082] If programmable logic is used, then this logic can be executed on a commercially available processing platform configured by executable software code to become a dedicated computer or dedicated device (e.g., a programmable logic array, an application-specific integrated circuit, etc.). Those skilled in the art will recognize that embodiments of the disclosed subject matter can be practiced with a variety of computer system configurations, including multi-core multiprocessor systems, minicomputers, mainframes, computers linked or clustered with distributed functions, and general-purpose or microcomputers that can be embedded in virtually any device. For example, the embodiments described above can be implemented using at least one processor device and memory.

[0083] The processor unit or device discussed herein may be a single processor, multiple processors, or a combination thereof. A processor device may have one or more processor "cores". The terms "computer program medium," "non-transitory computer-readable medium," and "computer-usable medium" as discussed herein are generally used to refer to tangible media, such as removable storage unit 718, removable storage unit 722, and hard disks installed in hard disk drive 712.

[0084] Various embodiments of this disclosure are described with reference to this example computer system 700. After reading this description, those skilled in the art will recognize how to implement this disclosure using other computer systems and / or computer architectures. While operations may be described as sequential processing, some operations may actually be executed in parallel, concurrently, and / or in a distributed environment, and program code may be stored locally or remotely for access by a single processor or multiple processor machines. Furthermore, in some embodiments, the order of operations may be rearranged without departing from the spirit of the disclosed subject matter.

[0085] Processor device 704 may be a dedicated or general-purpose processor device specifically configured to perform the functions discussed herein. Processor device 704 may be connected to communication infrastructure 706, such as a bus, message queue, network, multi-core messaging scheme, etc. The network may be any network suitable for performing the functions disclosed herein, and may include local area networks (LANs), wide area networks (WANs), wireless networks (e.g., WiFi), mobile communication networks, satellite networks, the Internet, fiber optics, coaxial cable, infrared, radio frequency (RF), or any combination thereof. Other suitable network types and configurations will be apparent to those skilled in the art. Computer system 700 may also include main memory 708 (e.g., random access memory, read-only memory, etc.) and may also include secondary memory 710. Secondary memory 710 may include hard disk drives 712 and removable storage drives 714, such as floppy disk drives, magnetic tape drives, optical disk drives, flash memory, etc.

[0086] The removable storage drive 714 can read from and / or write to the removable storage unit 718 in a well-known manner. The removable storage unit 718 may include a removable storage medium that can be read from and written to by the removable storage drive 714. For example, if the removable storage drive 714 is a floppy disk drive or a Universal Serial Bus port, then the removable storage unit 718 may be a floppy disk or a portable flash drive, respectively. In one embodiment, the removable storage unit 718 may be a non-transitory computer-readable recording medium.

[0087] In some embodiments, auxiliary memory 710 may include alternative components for allowing computer programs or other instructions to be loaded into computer system 700, such as removable storage unit 722 and interface 720. Examples of such components may include program cartridges and cartridge interfaces (e.g., as found in video game systems), removable memory chips (e.g., EEPROM, PROM, etc.) and associated sockets, as well as other removable storage units 722 and interfaces 720, as will be apparent to those skilled in the art.

[0088] Data stored in computer system 700 (e.g., in main memory 708 and / or auxiliary memory 710) can be stored on any type of suitable computer-readable medium, such as optical storage devices (e.g., optical discs, digital multifunction optical discs, Blu-ray discs, etc.) or magnetic tape storage devices (e.g., hard disk drives). Data can be configured with any type of suitable database configuration, such as relational databases, structured query language (SQL) databases, distributed databases, object databases, etc. The appropriate configuration and storage type will be clear to those skilled in the art.

[0089] Computer system 700 may also include a communication interface 724. Communication interface 724 may be configured to allow software and data to be transferred between computer system 700 and external devices. Exemplary communication interface 724 may include a modem, network interface (e.g., an Ethernet card), communication port, PCMCIA slot, and card, etc. Software and data transmitted via communication interface 724 may be in the form of signals, which may be electronic, electromagnetic, optical, or other signals, as will be apparent to those skilled in the art. Signals may travel via communication path 726, which may be configured to carry signals and may be implemented using wires, cables, optical fibers, telephone lines, cellular telephone links, radio frequency links, etc.

[0090] Computer system 700 may also include a display interface 702. Display interface 702 may be configured to allow data transfer between computer system 700 and external display 730. Exemplary display interface 702 may include High Definition Multimedia Interface (HDMI), Digital Video Interface (DVI), Video Graphics Array (VGA), etc. Display 730 may be any suitable type of display for displaying data transferred via display interface 702 of computer system 700, including cathode ray tube (CRT) displays, liquid crystal displays (LCDs), light-emitting diode (LED) displays, capacitive touch displays, thin-film transistor (TFT) displays, etc.

[0091] Computer program media and computer-usable media can refer to memory, such as main memory 708 and auxiliary memory 710, which may be memory semiconductors (e.g., DRAM, etc.). These computer program products can be components used to provide software to computer system 700. Computer programs (e.g., computer control logic) can be stored in main memory 708 and / or auxiliary memory 710. Computer programs can also be received via communication interface 724. When executed, such computer programs enable computer system 700 to implement the methods discussed herein. Specifically, when executed, computer programs enable processor device 704 to implement the methods discussed herein. Figure 3 , Figure 5 and Figure 6 The method shown is as discussed herein. Accordingly, such a computer program can represent the controller of computer system 700. When implementing this disclosure using software, the software can be stored in a computer program product and loaded into computer system 700 using a removable storage drive 714, interface 720, and hard disk drive 712 or communication interface 724.

[0092] Processor device 704 may include one or more modules or engines configured to perform the functions of computer system 700. Each module or engine may be implemented in hardware, and in some cases, may also utilize software such as program code and / or programs stored in main memory 708 or auxiliary memory 710. In such cases, the program code may be compiled by processor device 704 (e.g., by a compilation module or engine) before being executed by the hardware of computer system 700. For example, the program code may be source code written in a programming language, which is translated into a lower-level language (such as assembly language or machine code) for execution by processor device 704 and / or any additional hardware components of computer system 700. The compilation process may include lexical analysis, preprocessing, parsing, semantic analysis, syntax-guided transformation, code generation, code optimization, and any other techniques that may be adapted to translate the program code into a lower-level language suitable for controlling computer system 700 to perform the functions disclosed herein. It will be clear to those skilled in the art that such processing results in computer system 700 being a specially configured computer system 700 specifically programmed to perform the functions discussed above.

[0093] The technology consistent with this disclosure provides, among other features, systems and methods for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling. While various exemplary embodiments of the disclosed systems and methods have been described above, it should be understood that they are given for illustrative purposes only and not for limitation. This is not exhaustive and is not intended to limit this disclosure to its exact form. Modifications and variations are possible, or may be derived from practice, of this disclosure without departing from its breadth or scope.

Claims

1. A method for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling, comprising: The receiver of the processing server receives transaction data for multiple payment transactions based on fiat currencies from the first computing system; The receiver on the processing server receives transaction data from the second computing system for multiple cryptocurrency-based blockchain transactions; The receiver on the processing server receives node connectivity data of the blockchain network from a third computing system; The processor of the processing server generates a fraud detection model based at least on the received node connectivity data, wherein generating the fraud detection model includes generating a graphical representation of the received node connectivity data; The receiver on the processing server receives transaction data for new blockchain transactions from the computing device; The processor of the processing server uses a combination of at least the generated fraud detection model, transaction data of the plurality of fiat currency-based payment transactions, and transaction data of the plurality of cryptocurrency-based blockchain transactions to generate a fraud score for the new blockchain transaction; as well as The generated fraud score is transmitted from the processor server's transmitter to the computing device.

2. The method of claim 1, wherein the graphical representation includes at least a visual representation of each of a plurality of blockchain nodes in a blockchain network and connections between one or more of the plurality of blockchain nodes.

3. The method of claim 2, wherein the visual representation of each of the plurality of blockchain nodes in the graphical representation is based on transaction data of the received plurality of cryptocurrency-based blockchain transactions to indicate the likelihood that the respective blockchain node is involved in fraudulent activity.

4. The method of claim 1, wherein if the transaction data of the new blockchain transaction identifies a blockchain node in the blockchain network with a high probability of fraud based on the node connectivity data of the blockchain network, then the fraud score indicates a high probability of fraud.

5. The method of claim 4, wherein a higher probability of fraud based on node connectivity data is indicated by the following: the blockchain node or an auxiliary blockchain node directly connected to the blockchain node has a number of connected nodes in the blockchain network greater than a predetermined threshold without additional connections.

6. The method of claim 1, wherein the fraud detection model is generated using artificial intelligence.

7. The method of claim 1, further comprising: The processor on the processing server modifies the generated fraud detection model based on the generated fraud score.

8. The method of claim 7, further comprising: The receiver on the processing server receives a message instructing the disposal of a new blockchain transaction, in which... The modified fraud detection model is also based on the handling of the indicated new blockchain transactions.

9. A system for fraud scoring of cryptocurrency transactions using multiple datasets and graphical modeling, comprising: First computing system; Second computing system; Third computing system; Computing devices; Blockchain network; as well as Processing server, the processing server comprising: The receiver receives transaction data of multiple fiat currency-based payment transactions from a first computing system, transaction data of multiple cryptocurrency-based blockchain transactions from a second computing system, and node connectivity data of the blockchain network from a third computing system. A processor that generates a fraud detection model based at least on received node connectivity data, wherein generating the fraud detection model includes generating a graphical representation of the received node connectivity data; and transmitter, in which The receiver on the processing server also receives transaction data for new blockchain transactions from the computing device. The processor of the processing server uses a combination of at least the generated fraud detection model, transaction data from the plurality of fiat-based payment transactions, and transaction data from the plurality of cryptocurrency-based blockchain transactions to generate a fraud score for the new blockchain transaction. The server's transmitter sends the generated fraud scores to the computing device.

10. The system of claim 9, wherein the graphical representation includes at least a visual representation of each of a plurality of blockchain nodes in a blockchain network and connections between one or more of the plurality of blockchain nodes.

11. The system of claim 10, wherein the visual representation of each of the plurality of blockchain nodes in the graphical representation is based on transaction data of the received plurality of cryptocurrency-based blockchain transactions to indicate the likelihood that the respective blockchain node is involved in fraudulent activity.

12. The system of claim 9, wherein if the transaction data of a new blockchain transaction identifies a blockchain node in the blockchain network with a high probability of fraud based on the node connectivity data of the blockchain network, then the fraud score indicates a high probability of fraud.

13. The system of claim 12, wherein a higher probability of fraud based on node connectivity data is indicated by the blockchain node or an auxiliary blockchain node directly connected to the blockchain node having a number of connected nodes in the blockchain network greater than a predetermined threshold without additional connections.

14. The system of claim 9, wherein the fraud detection model is generated using artificial intelligence.

15. The system of claim 9, wherein the processor of the processing server modifies the generated fraud detection model based on the generated fraud score.

16. The system of claim 15, wherein The receiver on the processing server receives messages instructing the disposal of new blockchain transactions, and The modified fraud detection model is also based on the handling of the indicated new blockchain transactions.

Images