How to protect potential losses of US$4.6 billion—how AI enables real-time risk decisions at Binance
Key topics of the post:In the first half of 2026, Binance’s AI-driven risk systems helped protect more than 8 million users and prevent approximately US$4.6 billion in potential losses.Currently, AI underpins 80% to 90% of real-time risk decisions in identity verification, account security, payments, and transaction screening, with human reviewers handling extreme cases that require more refined judgment.More than 100 AI models power anti-fraud controls to detect scams, forged documents, and large-scale social engineering attempts.