The longitude problem: In the AI era, detection is won on facts, not guesses
Opinion piece argues defenders should beat AI-era attackers by carrying verified ground truth about approvers, domains, and vendors instead of relying on inference.
CSO Online contributor Alan LeFort, CEO of StrongestLayer, uses the historical longitude problem to argue that AI-era detection should rely on carried facts—authoritative records of payment approvers, owned domains, and legitimate vendors—rather than probabilistic inference that both attackers and defenders can now perform with comparable reasoning models. He illustrates with a CFO wire-fraud example defeated by checking the approver of record and the reply-to domain against ground truth. The piece stresses that ground truth decays and must be continuously maintained, like chronometers kept wound on every ship.
- Attackers and defenders now share comparable AI reasoning models, shifting the contest to data quality.
- Carrying facts (approvers of record, owned domains, real vendors) turns detection from odds into arithmetic.
- A BEC wire request is disproven by contradicting known approver and domain facts, not anomaly scores.
- Ground truth decays as approvers, domains, and vendors change, requiring ongoing maintenance.
- Author recommends starting with the facts an attacker most has to guess: who can move money.
- Vendors
- StrongestLayer
- Organizations
- ProofpointMcAfeeIntel
From the original article
4 min read at csoonline.com
For most of the age of sail, a captain could find his latitude in minutes and could not find his longitude at all. Latitude you could read off the sun. Longitude, your position east to west, offered no such trick.
csoonline.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.