Conversational authentication
Techniques are disclosed relating to contextual authentication across different applications based on user communications. In some embodiments, a user is preauthenticated to certain actions on a second application based on the user's communication via a first application. The user's communication via a first application provides contextual information that may be used to preauthenticate a request to perform an action on the second application. Contextual information may include the user's communication itself, communications characteristics that are determined from the user's communications, or both. In some embodiments, the degree of preauthentication progressively increases or decreases with the degree of use on the first application; that is, the user is preauthenticated to greater or fewer portions of an authentication procedure, to perform greater or fewer actions, or to perform actions more or less critical to security, as additional information regarding the user's communication on the first application becomes available. In some embodiments, preauthentication may be revoked as additional contextual information becomes available on the first application.
1. A method, comprising:
receiving, by a computing system, information indicative of:
one or more first user-generated communications between a first user and a second user via a first application that supports user communications, including messages previously confirmed to be generated by the first user; and
one or more second user-generated communications between users via the first application;
processing, by the computing system, the received information to analyze image usage data for the second user-generated communications in comparison with image usage data for the first user-generated communications;
determining, by the computing system based on the processing, to pre-authorize the first user to at least a portion of an authorization procedure to perform an operation via a second application, wherein the determining that the first user is pre-authorized is performed:
prior to a request by the first user to perform the operation via the second application; and
without an explicit user request to pre-authorize the operation; and
determining to authorize the first user to perform the operation via the second application, according to the authorization procedure, without re-performing the at least a portion of the authorization procedure for which the pre-authorization was performed.
2. The method of claim 1 , where the information is based on usage of one or more emoticons.
3. The method of claim 1 , wherein the image usage data includes any combination of one or more types of image usage data from the following group of types of image usage data:
number of images per message for the first user;
counts of use of a particular image by the first user; and
relationships between image use and text content by the first user.
4. The method of claim 1 , wherein the image usage data includes timing characteristics of image use across multiple messages sent at different times.
5. The method of claim 1 , wherein the analyzing in comparison is performed by a machine learning module of the computing system.
6. The method of claim 5 , further comprising training the machine learning module based on past communications labeled as being sent by first user.
7. The method of claim 1 , wherein the information indicates camera capabilities of a device used by the first user for the communications with the second user.
8. The method of claim 1 , wherein the information indicates one or more of the following image attributes: lighting, color, recognized faces, and time of day.
9. The method of claim 1 , wherein the receiving and determining to pre-authorize are performed multiple times to include additional characteristics of communications between the first user and the second user via the first application.
10. The method of claim 1 , further comprising canceling the pre-authorization based on additional information indicative of communications.
11. The method of claim 1 , wherein the determining is further based on information regarding activity of the user reported by a third application installed on a device of the first user.
12. The method of claim 11 , wherein the determining to pre-authorize is based on comparing one or more user characteristics reported by both the first and third applications.
13. The method of claim 1 , wherein the information includes the content of the second user-generated communications.
14. A non-transitory computer-readable medium having computer instructions stored thereon that are capable of causing a computing device to perform operations comprising:
receiving information indicative of:
one or more first user-generated communications between a first user and a second user via a first application that supports user communications, including messages previously confirmed to be generated by the first user; and
one or more second user-generated communications between users via the first application;
processing the received information to analyze image usage data for the second user-generated communications in comparison with image usage data for the first user-generated communications;
determining, based on the processing, to pre-authorize the first user to at least a portion of an authorization procedure to perform an operation via a second application, wherein the determining that the first user is pre-authorized is performed:
prior to a request by the first user to perform the operation via the second application; and
without an explicit user request to pre-authorize the operation; and
determining to authorize the first user to perform the operation via the second application, according to the authorization procedure, without re-performing the at least a portion of the authorization procedure for which the pre-authorization was performed.
15. The non-transitory computer-readable medium of claim 14 , wherein the determining is performed by a machine learning module that is trained based on past communications labeled as being sent by first user.
16. The non-transitory computer-readable medium of claim 14 , wherein the determining is further based on information regarding activity of the user reported by a third application installed on a device of the first user.
17. The non-transitory computer-readable medium of claim 14 , wherein the information is generated by a device of the first user based on the content of the second user-generated communications.
18. A system, comprising:
one or more processors; and
one or more memories having program instructions stored thereon that are executable by the one or more processors to perform operations comprising:
receiving information indicative of
one or more first user-generated communications between a first user and a second user via a first application that supports user communications, including messages previously confirmed to be generated by the first user; and
one or more second user-generated communications between users via the first application;
processing the received information to analyze image usage data for the second user-generated communications in comparison with image usage data for the first user-generated communications;
determining, based on the processing, to pre-authorize the first user to at least a portion of an authorization procedure to perform an operation via a second application, wherein the determining that the first user is pre-authorized is performed:
prior to a request by the first user to perform the operation via the second application; and
without an explicit user request to pre-authorize the operation; and
determining to authorize the first user to perform the operation via the second application, according to the authorization procedure, without re-performing the at least a portion of the authorization procedure for which the pre-authorization was performed.