Sublime NLU 3.0: Faster, more accurate, future-proof defense against AI email attacks · Blog · Sublime Security
ID: 50ff9b6a-4d27-5629-bdf7-8afde02ed64b
STIX ID: report--50ff9b6a-4d27-5629-bdf7-8afde02ed64b
Feed Name: Sublime Security Blog
Sublime announces NLU 3.0, a major upgrade to its email Natural Language Understanding engine that leverages GenAI-driven synthetic data augmentation, a unified multi-head multi-task architecture, and modular heads for rapid feature expansion. The update aims to improve detection of sophisticated, often AI-generated phishing and BEC-style attacks, reduce false positives, and expose richer NLU signals (intents, entities, topics) via Message Query Language (MQL) for easier rule creation and human analysis; a sample MQL snippet demonstrating credential-theft detection in EML attachments is included.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.
