Proofpoint Intelligent Classification and Protection is an artificial intelligence-powered data discovery and classification solution that performs petabyte-scale data classification and protection. The system takes inventory of content across various locations, with its AI engine analyzing and classifying that content using natural language processing and machine learning algorithms that can operate without labeled datasets. The solution allows creation of custom trainable classifiers and autogenerates dictionaries and detectors that integrate with Proofpoint DLP. It discovers, classifies, and protects sensitive data across cloud and hybrid environments, providing users a complete view of organizational data by confidentiality level and business category. This enables detection, management and control of unauthorized access to sensitive data while mitigating data security risk through complete visibility and control of business-critical data. The system includes a classification review workflow with validation stages and iterative processes until high confidence levels are reached, with model retraining using new samples.