Context-aware cryptographic inventory

A computer program product comprising one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by a processor to cause the processor to perform operations comprising:

• serializing by expressing in natural language (NL) a knowledge graph comprising a plurality of entities and a plurality of relationships among the plurality of entities, the plurality of relationships providing a cryptographic context of the knowledge graph, the cryptographic context being represented as a cryptographic inventory in the knowledge graph, the serializing outputting a serialized NL knowledge graph;
• inputting, into a foundation model, the serialized NL knowledge graph;
• executing the foundation model using a first prompt input corresponding to a task description relative to the serialized NL knowledge graph and further relative to the cryptographic inventory, the first prompt input comprising a cryptographic criterion, the executing producing a trained foundation model capable of answering zero-shot questions about the cryptographic context;
• executing the trained foundation model with a second prompt input, the second prompt input corresponding to an unknown task on which the trained foundation model has not been trained;
• outputting responsive to executing the trained foundation model, a response, the response being based on the cryptographic context;
• and
• visually rendering on a display apparatus, a visualization of the response in relation to the cryptographic context.

A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:

• serializing by expressing in natural language (NL) a knowledge graph comprising a plurality of entities and a plurality of relationships among the plurality of entities, the plurality of relationships providing a cryptographic context of the knowledge graph, the cryptographic context being represented as a cryptographic inventory in the knowledge graph, the serializing outputting a serialized NL knowledge graph;
• inputting, into a foundation model, the serialized NL knowledge graph;
• executing the foundation model using a first prompt input corresponding to a task description relative to the serialized NL knowledge graph and further relative to the cryptographic inventory, the first prompt input comprising a cryptographic criterion, the executing producing a trained foundation model capable of answering zero-shot questions about the cryptographic context;
• executing the trained foundation model with a second prompt input, the second prompt input corresponding to an unknown task on which the trained foundation model has not been trained;
• outputting responsive to executing the trained foundation model, a response, the response being based on the cryptographic context;
• and
• visually rendering on a display apparatus, a visualization of the response in relation to the cryptographic context.