Dynamic knowledge-based authentication

1. A computer-implemented method comprising:

receiving user data from a plurality of data sources, wherein the user data describes a user;

determining a plurality of events in a real life of the user within the user data by applying anomaly detection to the user data;

generating a knowledge graph to represent the plurality of events in the real life of the user, wherein the knowledge graph comprises a plurality of nodes;

wherein each node of the knowledge graph represents an event in the real life of the user, and wherein an edge between a first node and a second node in the knowledge graph represents a connection between a first event represented by the first node and second event represented by the second node;

receiving a request to authenticate the user;

selecting a key event from among the plurality of events, based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

generating, by a computer processor, for the user a challenge based on the key event selected based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

receiving a response to the challenge; and

deciding whether to authenticate the user based on the response to the challenge.

2. The computer-implemented method of claim 1 , wherein a first data source of the plurality of data sources is at least one of a biological reader or a cyber-physical reader.

3. The computer-implemented method of claim 1 , wherein a first data source of the plurality of data sources is an internet-of-things device associated with the user.

4. The computer-implemented method of claim 1 , wherein the selecting the key event comprises:

calculating a respective safety value for each of the plurality of events; and

determining that the respective safety value of the key event falls within an established safety range.

5. The computer-implemented method of claim 1 , wherein the selecting the key event comprises:

calculating a respective memorability value for each of the plurality of events; and

determining that the respective memorability value of the key event falls within an established memorability range.

6. The computer-implemented method of claim 1 , further comprising:

automatically updating the knowledge graph to reflect correctness of the response to the challenge; and

selecting an additional key event from among the plurality of events in the real life of the user, based at least in part on the knowledge graph, after automatically updating the knowledge graph; and

generating for the user an additional challenge based on the additional key event.

7. The computer-implemented method of claim 1 , further comprising automatically updating the knowledge graph to reflect correctness of the response to the challenge.

8. A system comprising:

a memory having computer readable instructions; and

one or more processors for executing the computer readable instructions, the computer readable instructions comprising:

receiving user data from a plurality of data sources, wherein the user data describes a user;

determining a plurality of events in a real life of the user within the user data by applying anomaly detection to the user data;

generating a knowledge graph to represent the plurality of events in the real life of the user, wherein the knowledge graph comprises a plurality of nodes;

wherein each node of the knowledge graph represents an event in the real life of the user, and wherein an edge between a first node and a second node in the knowledge graph represents a connection between a first event represented by the first node and second event represented by the second node;

receiving a request to authenticate the user;

selecting a key event from among the plurality of events, based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

generating for the user a challenge based on the key event selected based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

receiving a response to the challenge; and

deciding whether to authenticate the user based on the response to the challenge.

9. The system of claim 8 , wherein a first data source of the plurality of data sources is at least one of a biological reader or a cyber-physical reader.

10. The system of claim 8 , wherein a first data source of the plurality of data sources is an internet-of-things device associated with the user.

11. The system of claim 8 , wherein the selecting the key event comprises:

calculating a respective safety value for each of the plurality of events; and

determining that the respective safety value of the key event falls within an established safety range.

12. The system of claim 8 , wherein the selecting the key event comprises:

calculating a respective memorability value for each of the plurality of events; and

determining that the respective memorability value of the key event falls within an established memorability range.

13. The system of claim 8 , further comprising:

automatically updating the knowledge graph to reflect correctness of the response to the challenge; and

selecting an additional key event from among the plurality of events in the real life of the user, based at least in part on the knowledge graph, after automatically updating the knowledge graph; and

generating for the user an additional challenge based on the additional key event.

14. The system of claim 8 , the computer-readable instructions further comprising automatically updating the knowledge graph to reflect correctness of the response to the challenge.

15. A computer-program product for attempting to authenticate a user, the computer program product comprising a non-transitory computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving user data from a plurality of data sources, wherein the user data describes a user;

determining a plurality of events in a real life of the user within the user data by applying anomaly detection to the user data;

generating a knowledge graph to represent the plurality of events in the real life of the user, wherein the knowledge graph comprises a plurality of nodes;

wherein each node of the knowledge graph represents an event in the real life of the user, and wherein an edge between a first node and a second node in the knowledge graph represents a connection between a first event represented by the first node and second event represented by the second node;

receiving a request to authenticate the user;

selecting a key event from among the plurality of events, based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

generating for the user a challenge based on the key event selected based at least in part on the knowledge graph representing the plurality of events in the real life of the user, responsive to the request to authenticate the user;

receiving a response to the challenge; and

deciding whether to authenticate the user based on the response to the challenge.

16. The computer-program product of claim 15 , wherein a first data source of the plurality of data sources is at least one of a biological reader, a cyber-physical reader, and an internet-of-things device associated with the user.

17. The computer-program product of claim 15 , wherein the selecting the key event comprises:

calculating a respective safety value for each of the plurality of events; and

determining that the respective safety value of the key event falls within an established safety range.

18. The computer-program product of claim 15 , wherein the selecting the key event comprises:

calculating a respective memorability value for each of the plurality of events; and

determining that the respective memorability value of the key event falls within an established memorability range.

19. The computer-program product of claim 15 , further comprising:

automatically updating the knowledge graph to reflect correctness of the response to the challenge; and

selecting an additional key event from among the plurality of events, based at least in part on the knowledge graph, after automatically updating the knowledge graph; and

generating for the user an additional challenge based on the additional key event.

20. The computer-program product of claim 15 , the method further comprising automatically updating the knowledge graph to reflect correctness of the response to the challenge.