Sensitive data leakage prevention

Abstract

A comprehensive system for sensitive data leakage protection. Text extracted from documents and images that is to be transmitted/communicated is scanned to detect ciphertext within a document or image. Machine learning models are trained and executed to analyze the datum to determine data classifications and deep learning models are self-trained and executed to detect emerging data points (i.e., new threats affecting the ability to classify data) and feeds such emerging data points back to the machine learning model(s). Intelligence capable of receiving findings from the ciphertext detection component as well both the machine learning and the deep learning is executed to determine a level of sensitive data leakage attributed to each dataset being transmitted/communicated and, in response to determining the level of sensitive date leakage, make real-time decisions on whether to allow, hold or block the data transmission/digital communication.