Deep learning for targeted password generation with cognitive user information understanding
AssigneeInternational Business Machines Corporation
InventorsSuresh N. Chari, Benjamin J. Edwards, Taesung Lee, Ian M. Molloy, Youngja Park
Life of this patent
Estimating the term…
Abstract
An approach is provided that receives a set of user information pertaining to a user. The received set of information is encoded into a neural network and the neural network is trained using the encoded user information. As an output of the trained neural network, passwords corresponding to the user are generated.
Claims20
A method implemented by an information handling system that includes a processor and a memory accessible by the processor, the method comprising:
- receiving a set of user information pertaining to a user;
- training a neural network using the received set of user information, wherein the neural network includes an encoder and a decoder and wherein the training further includes encoding the received set of user information by parsing the received set of user information and breaking the parsed user information into inputs that are inputted into the neural network;
- generating one or more passwords corresponding to the user, wherein the generating includes decoding the set of user information;
- and
- further training the neural network using one or more results of a comparison between the generated one or more passwords and an actual password corresponding to the user.
An information handling system comprising:
- one or more processors;
- a memory coupled to at least one of the processors;
- and
- a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions comprising:
- receiving a set of user information pertaining to a user;
- training a neural network using the received set of user information, wherein the neural network includes an encoder and a decoder and wherein the training further includes encoding the received set of user information by parsing the received set of user information and breaking the parsed user information into inputs that are inputted into the neural network;
- generating one or more passwords corresponding to the user, wherein the generating includes decoding the set of user information;
- and
- further training the neural network using one or more results of a comparison between the generated one or more passwords and an actual password corresponding to the user.
A computer program product stored in a computer readable storage medium, comprising computer program code that, when executed by an information handling system, performs actions comprising:
- receiving a set of user information pertaining to a user;
- training a neural network using the received set of user information, wherein the neural network includes an encoder and a decoder and wherein the training further includes encoding the received set of user information by parsing the received set of user information and breaking the parsed user information into inputs that are inputted into the neural network;
- generating one or more passwords corresponding to the user, wherein the generating includes decoding the set of user information;
- and
- further training the neural network using one or more results of a comparison between the generated one or more passwords and an actual password corresponding to the user.
Dependencies are inferred from the claim text.