Customizable deep learning to prevent data loss of image borne sensitive documents

Abstract

Disclosed are methods and systems for customizing a deep learning ('DL') stack to detect organization sensitive data in images, referred to as image-borne organization sensitive documents, and protecting against loss of the image-borne organization sensitive documents. The methods and systems include distributing a trained master DL stack with stored parameters to a plurality of organizations. Providing at least some of the organizations with a DL stack update trainer, under the organizations' control, configured to save, during generation of updated DL stacks, non-invertible features derived from images of organization-sensitive training examples, ground truth labels for the images, and parameters of the updated DL stacks. Receiving, from at least one of the DL stack update trainers, organization-specific examples including the non-invertible features and the ground truth labels, without receiving images of the organization-specific examples. And using the received organization-specific examples to update the trained master DL stack.