Multi-factor authentication for non-internet applications
Receive a transaction generated by a user of a non-internet application; identify transaction life cycle steps of previous similar transactions; and generate a transaction risk score for the transaction using machine learning models and a blockchain record of the previous similar transactions. In response to the transaction risk score exceeding a threshold value, authenticate the transaction and the user using two-step authentication. The two-step authentication uses challenge/answer templates derived from the blockchain record of previous transactions.
1. A method comprising:
receiving a transaction generated by a user of a non-internet application, wherein the non-internet based application is one of a simple message service (SMS) application and an unstructured supplementary service data (USSD) application;
identifying transaction life cycle steps of previous similar transactions, wherein identifying transaction life cycle steps includes analyzing a series of messages from a complete workflow cycle of the non-internet based application using a custom natural language processing (NLP) model;
generating a transaction risk score for the transaction using machine learning models and a blockchain record of the previous similar transactions;
generating transaction life cycle step challenge templates by using part-of-speech tagging natural language processing (NLP) techniques and transaction similarity analysis on the series of messages; and
in response to the transaction risk score exceeding a threshold value, authenticating the transaction and the user using two-step authentication,
wherein the two-step authentication uses challenge/answer templates derived from the blockchain record of previous transactions.
2. The method of claim 1 further comprising generating a possible sequence of steps that model a valid transaction lifecycle.
3. The method of claim 1 wherein generating the transaction risk score includes determine legitimacy or anomaly of the transaction using a Bayesian network.
4. A non-transitory computer readable storage medium embodying computer executable instructions, which when executed by a computer cause the computer to facilitate a method of:
receiving a transaction generated by a user of a non-internet application, wherein the non-internet based application is one of a simple message service (SMS) application and an unstructured supplementary service data (USSD) application;
identifying transaction life cycle steps of previous similar transactions, wherein identifying transaction life cycle steps includes analyzing a series of messages from a complete workflow cycle of the non-internet based application using a custom natural language processing (NLP) model;
generating a transaction risk score for the transaction using machine learning models and a blockchain record of the previous similar transactions;
generating transaction life cycle step challenge templates by using part-of-speech tagging natural language processing (NLP) techniques and transaction similarity analysis on the series of messages; and
in response to the transaction risk score exceeding a threshold value, authenticating the transaction and the user using two-step authentication,
wherein the two-step authentication uses challenge/answer templates derived from the blockchain record of previous transactions.
5. The non-transitory computer readable storage medium of claim 4 further comprising generating a possible sequence of steps that model a valid transaction lifecycle.
6. The non-transitory computer readable storage medium of claim 4 wherein generating the transaction risk score includes determine legitimacy or anomaly of the transaction using a Bayesian network.
7. An apparatus comprising:
a memory embodying computer executable instructions; and
at least one processor, coupled to the memory, and operative by the computer executable instructions to facilitate a method of:
receiving a transaction generated by a user of a non-internet application, wherein the non-internet based application is one of a simple message service (SMS) application and an unstructured supplementary service data (USSD) application;
identifying transaction life cycle steps of previous similar transactions, wherein identifying transaction life cycle steps includes analyzing a series of messages from a complete workflow cycle of the non-internet based application using a custom natural language processing (NLP) model;
generating a transaction risk score for the transaction using machine learning models and a blockchain record of the previous similar transactions;
generating transaction life cycle step challenge templates by using part-of-speech tagging natural language processing (NLP) techniques and transaction similarity analysis on the series of messages; and
in response to the transaction risk score exceeding a threshold value, authenticating the transaction and the user using two-step authentication,
wherein the two-step authentication uses challenge/answer templates derived from the blockchain record of previous transactions.
8. The apparatus of claim 7 further comprising generating a possible sequence of steps that model a valid transaction lifecycle.