The benefits of taking an intent-based approach to detecting Business Email Compromise
Summary: Cisco Talos describes BEC as one of the most financially damaging online crimes, citing an internet crime report that puts 2021 losses at roughly $2.4 billion and total losses since 2013 at $43 billion. Talos outlines the limits of policy-based detection, exploitation-technique detection, and machine-learning executive profiling, and describes its own intent-based model that encodes email text with NNLM or BERT and classifies messages into scam types such as payroll, money transfer, gift card, invoice, and W-2 scams.
What's compelling: Policy-based detection only catches impersonation of executives whose addresses are in the database, so a payroll scam impersonating a marketing manager passes through - and the $43 billion lost since 2013 shows how often that gap gets used.
Read the original at Cisco Talos ↗
- Topics
- Phishing & Social Engineering
- Related
- US disrupts North Korean campaign behind $400 million crypto theft Cyber Risks · Nov 14, 2026North Korea ‘s Crypto Theft Operations: DOJ Seizes $1.2 Billion and Disrupts Hacker Infrastructure Cyber Risks · Nov 13, 2026FBI Says North Korean Hackers Stole Over $400 Million in Crypto Using Deepfake Video Calls Cyber Risks · Nov 13, 2026