Blockchain transaction safety

A method comprising:

• acquiring, at a server, blockchain data from a blockchain network, wherein the blockchain data includes a plurality of transactions between a plurality of blockchain addresses;
• labeling, at the server, a set of the blockchain addresses as fraudulent;
• generating, at the server, a graph data structure based on the blockchain data, wherein the graph data structure includes nodes for the blockchain addresses and includes edges between the nodes for blockchain transactions;
• calculating, at the server, a set of scoring features for each blockchain address, wherein each set of scoring features includes a graph-based scoring feature, and wherein calculating the graph-based scoring feature includes calculating a number of transactions associated with the blockchain address in the graph data structure;
• generating, at the server, a scoring model using sets of scoring features for the blockchain addresses that are labeled as fraudulent;
• generating, at the server, a trust score for each of the blockchain addresses using the scoring features associated with the blockchain addresses and the scoring model, wherein the trust score indicates a likelihood that the blockchain address is involved in fraudulent activity;
• receiving, at the server, a trust request for a specified blockchain address from a requesting device;
• and
• sending, from the server, the trust score for the specified blockchain address to the requesting device.