METHOD AND SYSTEM FOR FINDING SIMILAR FRAUDULENT GROUPS BASED ON GRAPH MODELS Russian patent published in 2022 - IPC G06F17/00 G06F21/00 

FIELD: information security.

SUBSTANCE: invention relates to a method and system for searching for fraudulent transactions. In the method: a) transaction data is received, wherein all data is related to fraudulent transactions; b) graphs are built based on the obtained data, wherein the nodes are the transaction data and the edges are the executed transactions or connections with attributes; c) for each graph built on stage b), the following stages are executed: defining the lists of iterations for each vertex; determining the distances to other nodes for each node of the graph using the iterative algorithm; determining the circuits with maximum distance; forming a frame of the graph based on the circuits determined on stage c), wherein said frame consists of all vertices and edges of said circuits; based on the formed frame, determining the diameter of the graph, constituting the distance of any of the circuits thereof; determining the amount of circuits in the frame of the graph; determining the density of the frame as the ratio of the amount of vertices of the frame of the graph to the total amount of vertices in the graph; d) the graphs obtained on stage b) are compared in pairs, wherein calculated for each pair of graphs are i) the ratio of diameters of the graphs; ii) the ratio of the amount of circuits of the frame; iii) the ratio of the densities of the frames of the compared graphs; iv) the similarity coefficients based on the values of the ratios obtained on stages i), ii) and iii); e) at least one graph similar to at least one known fraudulent scheme represented as a graph is determined based on the similarity coefficient obtained on stage d); and f) the transaction data associated with at least one known fraudulent scheme determined on stage e) is determined; g) based on the data obtained on stage f), the details and attributes constituting a generalisation of the identified transaction details and attributes of similar fraudulent schemes are blocked.

EFFECT: increase in the security of executing transactions.

4 cl, 5 dwg