South Korea’s Financial Supervisory Service has deployed a real-time artificial intelligence surveillance platform that scans trading data, news and online content to flag suspected cryptocurrency price manipulation. The system combines generative AI with machine learning to automate parts of a process that previously required investigators to examine large volumes of exchange data manually.
The platform first searches for assets showing abnormal changes in price or volume, then compares the activity with patterns drawn from the regulator’s previous investigations. The FSS highlighted patterns such as the “racehorse” type, in which a token moves sharply during a short period, and the “cage” type, which involves a steep rise while deposits or withdrawals are suspended or restricted.
For possible wash trading or coordinated trading, the FSS applies Benford’s Law alongside machine-learning models. Once a token records an unusual move, generative AI checks relevant news and exchange announcements for a plausible cause. A sharp move without a clear reason can lead the regulator to request detailed order and account data from the exchange involved.
The system also scans complaints, tips, media reports, YouTube videos, forum posts and private chat rooms to detect suspected front-running, false information or coordinated buy recommendations. Human investigators remain responsible for reviewing AI-generated reports before deciding whether to open a detailed analysis or formal investigation.
The new platform follows two years of enforcement under South Korea’s Virtual Asset User Protection Act, which took effect on July 19, 2024. Korean authorities examined more than 40 suspected unfair-trading cases during the law’s first two years. Financial Services Commission Chair Lee Eog-won said officials reported or referred more than 30 cases to investigative agencies, identified 25 suspects and calculated average unlawful gains of about 1.4 billion won, or roughly $940,000, per case.
Exchange-level controls have also developed. In May, new API-key rules required members of the Digital Asset Exchange Alliance—Upbit, Bithumb, Coinone, Korbit and Gopax—to monitor suspected key sharing, use IP whitelists and invalidate keys after warnings. The FSS estimated that API-based trading represented about 30% of domestic crypto turnover.
Future updates will add cross-exchange fund-flow analysis and on-chain transaction tracking, although no deployment date was provided. U.S. regulators have also kept human review central. A May 2025 GAO review found federal financial regulators used AI to identify risks but did not treat model output as the sole basis for a decision. XYO co-founder Markus Levin warned that false alerts or unverified allegations could arise if investigators place too much weight on automated output.
