Advanced image recognition for threat disposition scoring

A computer program product comprising a computer readable storage medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, causes the computing device to implement an image based event classification engine comprising an event image encoder and a first neural network computer model, that operates to:

• receive, by the event image encoder, an event data structure comprising a plurality of event attributes, wherein the event data structure represents an event occurring in association with at least one computing resource in a monitored computing environment;
• execute, by the event image encoder, for each event attribute in the plurality of event attributes, a corresponding event attribute encoder that encodes the event attribute as a pixel pattern in a predetermined grid of pixels, corresponding to the event attribute, of an event image representation data structure;
• input, into the first neural network computer model, the event image representation data structure;
• process, by the first neural network computer model, the event image representation data structure by applying one or more image feature extraction operations and image feature analysis algorithms to the event image representation data structure to generate a classification prediction output classifying the event into one of a plurality of predefined classifications;
• and
• output, by the first neural network computer model, a classification output indicating a prediction of one of the predefined classifications that applies to the event.

An apparatus comprising:

• a processor;
• and
• a memory coupled to the processor, wherein the memory comprises instructions which, when executed by the processor, cause the processor to implement an image based event classification engine comprising an event image encoder and a first neural network computer model, that operates to:
• receive, by the event image encoder, an event data structure comprising a plurality of event attributes, wherein the event data structure represents an event occurring in association with at least one computing resource in a monitored computing environment;
• execute, by the event image encoder, for each event attribute in the plurality of event attributes, a corresponding event attribute encoder that encodes the event attribute as a pixel pattern in a predetermined grid of pixels, corresponding to the event attribute, of an event image representation data structure;
• input, into the first neural network computer model, the event image representation data structure;
• process, by the first neural network computer model, the event image representation data structure by applying one or more image feature extraction operations and image feature analysis algorithms to the event image representation data structure to generate a classification prediction output classifying the event into one of a plurality of predefined classifications;
• and
• output, by the first neural network computer model, a classification output indicating a prediction of one of the predefined classifications that applies to the event.