Operating More Than 24 AI-Based Initiatives
and Over 100 Security Models

Global cryptocurrency exchange Binance announced that it prevented damages amounting to hundreds of millions of dollars over the past year through its artificial intelligence (AI) defense system.


From the first quarter of 2025 to the first quarter of this year, Binance blocked a total of $10.53 billion (approximately 16 trillion won) in potential losses. According to Binance Research, the scale of cryptocurrency-related fraud worldwide last year was estimated at around $17 billion, a 30% increase compared to the previous year. The attack success rate of advanced AI models reached 72.2%.

Binance Blocks $16 Billion in Losses Over One Year With AI Defense System View original image

Binance has consistently strengthened its defense system. The company currently operates more than 24 AI-driven initiatives and over 100 security models. Among these, computer vision technology is actively used to detect fake payment proofs, and real-time language analysis is utilized to prevent fraudulent patterns in P2P transactions. According to Binance, its AI decision-making system, which is responsible for 57% of overall fraud control, has reduced the rate of card fraud by 60-70% compared to the industry average, and the efficiency of its AI-based KYC (Know Your Customer) system for detecting deepfake and synthetic identities has been improved up to 100 times more than the previous manual process.


Binance is also heavily investing in strengthening preventive education, including raising user awareness. In the first quarter of this year, the company conducted account theft prevention education programs for more than 179,000 users.


As a result, Binance blocked 22.9 million attempts of fraud and phishing just in the first quarter of this year, contributing to the protection of assets valued at around $1.98 billion.



A Binance representative stated, "User protection in the era of AI should not stop at simply preventing fraud, but must extend to the entire process, including response and collaboration after threats occur, as well as asset recovery. As AI crime technologies rapidly evolve, we will continue to strengthen real-time detection, user protection, and educational systems to build a more transparent and secure trading environment."


This content was produced with the assistance of AI translation services.

© The Asia Business Daily. All rights reserved. Unauthorized AI training and use prohibited.

Today’s Briefing