South KoreaFinance and insurance2023 – ongoingDunamu
Upbit machine-learning fraud detection
Dunamu reported protecting KRW 98.626 billion in 2023 through Upbit's fraud-detection operation
Problem
Criminals used digital-asset transfers in voice-phishing schemes. Upbit needed to identify suspicious activity before customer funds left the exchange.
Approach
Dunamu developed a machine-learning fraud-detection system that inspected every deposit and withdrawal attempt in real time. It learned transaction patterns to identify unfamiliar suspicious activity. Specialist staff monitored alerts and restricted transfers, with investigators involved in recovery cases.
Results
Takeaway
The protected-assets figure covered the fraud-detection operation and human intervention together. Dunamu did not separate the model's contribution from staff actions.
Categories
- Industry
- Finance and insurance
- Business function
- Finance, risk and legal
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Goal
- Quality and risk
- Evidence
- Company's own claim
Sources
Source summaries
Dunamu described its internally developed machine-learning FDS and specialist response process. It reported KRW 98.626 billion protected in 2023 and described transfer restrictions and cooperation with investigators.
Full details are in the original sources.