Security attack detections for transactions in electronic payment processing networks

1. A computer system comprising:

a processor; and

memory coupled to the processor and storing instructions that, when executed by the processor, cause the computer system to:

retrieve, from the memory, a transaction flow graph representing financial transactions in an electronic payment processing network and including a first tree representing a financial hierarchy, and a second tree representing a location hierarchy, wherein at least one node of the first tree or the second tree has multiple children, and one or more edges or one or more nodes of the first tree and the second tree has a first attribute and a second attribute, wherein the first attribute is based on historical data, and the second attribute is based on current data associated with the one or more edges or one or more nodes;

receive data about a financial transaction in the electronic payment processing network, wherein the financial transaction is related to a first leaf node in the first tree, and a second leaf node in the second tree;

update, in real time, the second attributes based on current data of edges or nodes that can reach the first leaf node in the first tree, and the second attributes based on current data of edges or nodes that can reach the second leaf node in the second tree;

detect a security attack associated with the financial transaction by detecting an abnormal node or edge in the first tree or the second tree, the abnormal node or edge having a second attribute being out of a predefined range compared to the first attribute of the abnormal node or edge; and

block the financial transaction in response to detecting the security attack associated with the abnormal node or edge in the first tree or the second tree.

2. The computer system of claim 1 , wherein the memory further stores instructions that, when executed by the processor, cause the computer system to notify a user of the detection of the abnormal node or edge.

3. The computer system of claim 1 , wherein a first attribute of an edge or a node of the first tree or the second tree includes a number of transactions, a total amount of transactions, or an out flow degree.

4. The computer system of claim 1 , wherein a node of the first tree represents a primary account (PAN), a bank identification number (BIN), an issuer identification number (IIN), a business identification number (BID), or an Interbank Card Association (ICA) number.

5. The computer system of claim 1 , wherein a node of the second tree represents an automated teller machine (ATM) location, a store location, a city, or a country.

6. A tangible, non-transitory computer-readable medium storing instructions that, when executed by a computer system, cause the computer system to:

retrieve, from a memory, a transaction flow graph representing financial transactions in an electronic payment processing network and including a first tree representing a financial hierarchy, and a second tree representing a location hierarchy, wherein at least one node of the first tree or the second tree has multiple children, and one or more edges or one or more nodes of the first tree and the second tree has a first attribute and a second attribute, wherein the first attribute is based on historical data, and the second attribute is based on current data associated with the one or more edges or one or more nodes;

receive data about a financial transaction in the electronic payment processing network, wherein the financial transaction is related to a first leaf node in the first tree, and a second leaf node in the second tree;

update, in real time, the second attributes based on current data of edges or nodes that can reach the first leaf node in the first tree, and the second attributes based on current data of edges or nodes that can reach the second leaf node in the second tree;

detect a security attack associated with the financial transaction by detecting an abnormal node or edge in the first tree or the second tree, the abnormal node or edge having a second attribute being out of a predefined range compared to the first attribute of the abnormal node or edge; and

block the financial transaction in response to detecting the security attack associated with the abnormal node or edge in the first tree or the second tree.

7. The tangible, non-transitory computer-readable medium of claim 6 , wherein the tangible, non-transitory computer-readable medium further stores instructions that, when executed by the computer system, cause the computer system to: notify a user of the detection of the abnormal node or edge.

8. The tangible, non-transitory computer-readable medium of claim 6 , wherein a first attribute of an edge or a node of the first tree or the second tree includes a number of transactions, a total amount of transactions, or an out flow degree.

9. The tangible, non-transitory computer-readable medium of claim 6 , wherein a node of the first tree represents a primary account (PAN), a bank identification number (BIN), an issuer identification number (IIN), a business identification number (BID), or an Interbank Card Association (ICA) number.

10. The tangible, non-transitory computer-readable medium of claim 6 , wherein a node of the second tree represents an automated teller machine (ATM) location, a store location, a city, or a country.

11. A computer-implemented method comprising:

retrieving, by a computer system from a memory, a transaction flow graph representing financial transactions in an electronic payment processing network and including a first tree representing a financial hierarchy, and a second tree representing a location hierarchy, wherein at least one node of the first tree or the second tree has multiple children, and one or more edges or one or more nodes of the first tree and the second tree has a first attribute and a second attribute, wherein the first attribute is based on historical data, and the second attribute is based on current data associated with the one or more edges or one or more nodes;

receiving, by the computer system, data about a financial transaction in the electronic payment processing network, wherein the financial transaction is related to a first leaf node in the first tree, and a second leaf node in the second tree;

updating, by the computer system in real time, the second attributes based on current data of edges or nodes that can reach the first leaf node in the first tree, and the second attributes based on current data of edges or nodes that can reach the second leaf node in the second tree;

detecting a security attack associated with the financial transaction, by the computer system, by detecting an abnormal node or edge in the first tree or the second tree, the abnormal node or edge having a second attribute being out of a predefined range compared to the first attribute of the abnormal node or edge; and

blocking the financial transaction by the computer system in response to detecting the security attack associated with the abnormal node or edge in the first tree or the second tree.

12. The computer-implemented method of claim 11 , further comprising: notifying, by the computer system, a user of the detection of the abnormal node or edge.

13. The computer-implemented method of claim 11 , wherein a first attribute of an edge or a node of the first tree or the second tree includes a number of transactions, a total amount of transactions, or an out flow degree.

14. The computer-implemented method of claim 11 , wherein a node of the first tree represents a primary account (PAN), a bank identification number (BIN), an issuer identification number (IIN), a business identification number (BID), or an Interbank Card Association (ICA) number.

15. The computer-implemented method of claim 11 , wherein a node of the second tree represents an automated teller machine (ATM) location, a store location, a city, or a country.