Systems and methods for secure multi-model training within a zero-trust environment

A computerized method of secure model generation in a sequestered computing node comprising:

• receiving an algorithm in a secure computing enclave, wherein the algorithm is a plurality of algorithms received from a plurality of data stewards;
• receiving training data in the secure computing enclave;
• mapping the training data by Health Insurance Portability and Accountability Act (HIPAA) sensitivity categories, wherein the mapping identifies sensitive data categories and non-sensitive data categories;
• obfuscating the sensitive data categories to generate partially obfuscated training data;
• performing automated multi-model training on the algorithm to generate a plurality of trained models, wherein the multi-model training includes training by applying regressors, decision trees, and neural networks to a single machine learning training problem using the partially obfuscated training data;
• generating a leaderboard of the plurality of trained models;
• ranking the plurality of trained models in the leaderboard based upon a hybrid metric calculated by combining an epsilon parameter for each model with a DICE score;
• selecting a top model from the leaderboard;
• and
• performing security processing on the top model to generate a secure model.