Features extraction for blockchain transactions and program protocols
An access control server may receive state information of an autonomous program protocol that is recorded on a blockchain. The access control server may generate a trace log associated with one or more transactions executed by the autonomous program protocol, the trace log comprising machine events executed by the blockchain, the machine actions associated with the one or more transactions. The access control server may extract a set of features from the trace log, wherein a feature in the set comprises a summary of a machine event executed by the blockchain. The access control server may input the set of features to a machine learning model to determine a threat nature associated with the transactions of the autonomous program protocol. The access control server may perform a responsive action to address the threat nature.
1. A computer-implemented method comprising:
receiving state information of an autonomous program protocol that is recorded on a blockchain;
generating a trace log associated with one or more transactions executed by the autonomous program protocol, the trace log comprising machine events executed by the blockchain, the machine events associated with the one or more transactions, wherein the autonomous program protocol is recorded on the blockchain in bytecode and the trace log is in opcode;
extracting a set of features from the trace log, wherein a feature in the set comprises a summary of a machine event executed by the blockchain;
inputting the set of features to a machine learning model to determine a threat nature associated with the transactions of the autonomous program protocol; and
performing a responsive action to address the threat nature.
2. The method of claim 1 , wherein generating the trace log comprises using transaction hashes of the one or more transactions to identify the machine events that are relevant to the one or more transactions.
3. The method of claim 1 , wherein the machine learning model is a supervised learning model.
4. The method of claim 1 , wherein the machine learning model is an unsupervised learning model.
5. The method of claim 1 , wherein the responsive action is an access control action that restricts an access to the autonomous program protocol.
6. The method of claim 1 , wherein the set of features includes: contract size, a confirmation of a jump table, a number of public functions, a number of private functions, a number of pure functions, and/or a number of call functions between a smart contract and another contract or external address.
7. The method of claim 1 , wherein the machine learning model is trained to predict a set of characteristics that include a conformation of a flash loan, a swap within a smart contract, a beacon upgrade, and/or a balance change.
8. A system comprising:
one or more processors; and
memory configured to store code comprising instructions, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
receive state information of an autonomous program protocol that is recorded on a blockchain;
generate a trace log associated with one or more transactions executed by the autonomous program protocol, the trace log comprising machine events executed by the blockchain, the machine events associated with the one or more transactions, wherein the autonomous program protocol is recorded on the blockchain in bytecode and the trace log is in opcode;
extract a set of features from the trace log, wherein a feature in the set comprises a summary of a machine event executed by the blockchain;
input the set of features to a machine learning model to determine a threat nature associated with the transactions of the autonomous program protocol; and
perform a responsive action to address the threat nature.
9. The system of claim 8 , wherein generating the trace log comprises using transaction hashes of the one or more transactions to identify the machine events that are relevant to the one or more transactions.
10. The system of claim 8 , wherein the machine learning model is a supervised learning model.
11. The system of claim 8 , wherein the machine learning model is an unsupervised learning model.
12. The system of claim 8 , wherein the responsive action is an access control action that restricts an access to the autonomous program protocol.
13. The system of claim 8 , wherein the set of features includes: contract size, a confirmation of a jump table, a number of public functions, a number of private functions, a number of pure functions, and/or a number of call functions between a smart contract and another contract or external address.
14. The system of claim 8 , wherein the machine learning model is trained to predict a set of characteristics that include a conformation of a flash loan, a swap within a smart contract, a beacon upgrade, and/or a balance change.
15. A non-transitory computer-readable medium configured to store code comprising instructions, wherein the instructions, when executed by one or more processors, cause the one or more processors to:
receive state information of an autonomous program protocol that is recorded on a blockchain;
generate a trace log associated with one or more transactions executed by the autonomous program protocol, the trace log comprising machine events executed by the blockchain, the machine events associated with the one or more transactions, wherein the autonomous program protocol is recorded on the blockchain in bytecode and the trace log is in opcode;
extract a set of features from the trace log, wherein a feature in the set comprises a summary of a machine event executed by the blockchain;
input the set of features to a machine learning model to determine a threat nature associated with the transactions of the autonomous program protocol; and
perform a responsive action to address the threat nature.
16. The non-transitory computer-readable medium of claim 15 , wherein the trace log associated with the one or more transactions is in opcode.
17. The non-transitory computer-readable medium of claim 15 , wherein generating the trace log comprises using transaction hashes of the one or more transactions to identify the machine events that are relevant to the one or more transactions.
18. The non-transitory computer-readable medium of claim 15 , wherein the responsive action is an access control action that restricts an access to the autonomous program protocol.
19. The non-transitory computer-readable medium of claim 15 , wherein the set of features includes: contract size, a confirmation of a jump table, a number of public functions, a number of private functions, a number of pure functions, and/or a number of call functions between a smart contract and another contract or external address.
20. The non-transitory computer-readable medium of claim 15 , wherein the machine learning model is trained to predict a set of characteristics that include a conformation of a flash loan, a swap within a smart contract, a beacon upgrade, and/or a balance change.