South Korea’s Financial Supervisory Service (FSS) has deployed an artificial intelligence-powered surveillance system to monitor cryptocurrency markets and detect unfair trading practices in real time.
Launched on August 20, the new platform combines generative AI with machine-learning algorithms to help overcome the resource constraints faced by human investigators monitoring thousands of digital assets trading continuously across multiple exchanges. The initiative builds upon algorithms developed in January that previously identified price-manipulation suspects and order timings, expanding AI oversight across the entire surveillance pipeline.
Detecting Manipulation Schemes and Volume Inflation
A core feature of the system is its ability to flag short-term price manipulation by referencing historical market abuse tactics. Primary targets include "racehorse" schemes, which involve rapidly inflating token prices over short periods, and "cage" schemes, where assets under temporary deposit and withdrawal limits experience sharp price swings.
To identify volume inflation, the system pairs Benford’s law with machine-learning models to flag wash trading and coordinated group trading. When suspicious spikes trigger an alert, generative AI automatically scans news coverage and official exchange announcements to check for legitimate fundamental news. If no valid reason is found and manipulation appears likely, the FSS requests granular trade data from the exchange.
The regulatory grid also monitors digital channels, including YouTube, online message boards, and private messaging app chat rooms. By converting video audio and subtitles into text in real time, the AI evaluates media for signs of front-running, false information dissemination, and coordinated buying advice intended to trap retail investors.
Despite heavy automation, human oversight remains part of the process, as FSS investigators evaluate the AI-generated reports before deciding whether to launch formal enforcement proceedings.
Industry Skepticism and Future Upgrades
While the FSS views the deployment as essential for policing complex crypto markets, industry observers have raised questions about relying on AI for regulatory enforcement.
Markus Levin, co-founder of XYO, expressed concerns regarding whether regulators can ensure these systems operate on accurate data and remain within clearly defined boundaries, especially when outputs trigger government investigations or legal actions. Levin pointed to safety tests by developers like Meta, Anthropic, and OpenAI, where experimental models bypassed intended safety boundaries, noting that automated enforcement tools introduce risks of false positives.
Despite these concerns, the FSS plans to continue upgrading its oversight toolkit. Upcoming iterations of the platform will integrate tools to trace cross-exchange fund flows and monitor on-chain blockchain transactions.
