Systems, methods, apparatus, and articles of manufacture to classify data via tiered machine learning analysis

A system comprising:

• an endpoint device including:
• at least one first processor circuit to encode a first sample of unclassified data into a latent space representation (LSR), the LSR being an image of the unclassified data that obfuscates personally identifiable information (PII) of a user that accessed the unclassified data;
• and
• first interface circuitry to transmit the LSR over a network;
• and
• a network device including:
• second interface circuitry to access the LSR from the endpoint device;
• and
• at least one second processor circuit to:
• initiate a first artificial intelligence (AI) model to classify the unclassified data as benign or potentially malicious based on the LSR, the first AI model trained on LSRs of first webpages that are labelled as benign or malicious;
• and
• after the first AI model classifies the unclassified data as potentially malicious, initiate a second AI model to classify the unclassified data as benign or malicious based on a second sample of the unclassified data, the second sample being a non-obfuscated sample of the unclassified data, the second AI model trained on non-obfuscated samples of second webpages that are labelled as benign or malicious, the first AI model being less precise than the second AI model.