[1mm Financial Talk] "Beep~ Suspected Phishing Scam"... AI Banker Protecting Customers' Money

Caution Popup for Large Transfers
Attempted Transfer to Another's Mobile Phone
Suspension of Transactions with Suspicious Activity

Blocking IP Access with Past Phishing Crime Records
Detection of Multiple Transfers in a Short Period

Effective in Preventing Financial Crimes

Asia Economy DB

[Asia Economy Reporter Shim Nayoung] # Lee Sunmi (61), a self-employed person in Incheon, rushed to an ATM after receiving a call in February saying that she had to repay her existing loan to a bank clerk in order to receive the government's emergency low-interest COVID-19 loan. As she frantically pressed buttons to transfer 20 million won, a 'Phishing Scam Warning' popup appeared. The camera attached to the ATM detected Lee making a large transfer while talking on her phone and displayed the warning message. Lee, who was about to fall for the phishing scam and transfer the money, snapped out of it after seeing the message. She contacted the bank employee, explained the call, and was able to prevent the damage.

# Last month, a phishing scammer attempted multiple transfers by logging into a victim's bank app on their own phone using the victim's bank app ID and password collected through messenger phishing. The bank's financial crime response team immediately detected abnormal signals. A bank official said, "Although a customer can log in with a new phone, the fact that multiple transfer attempts were made immediately after logging in from a phone other than the one originally used raised suspicion of a crime." The official added, "We called the customer, but since there was no answer, we immediately suspended the transactions, which turned out to be phishing."

# In January this year, the bank's abnormal transaction detection system caught someone attempting to log into the bank app from an IP address previously associated with phishing crimes. The bank immediately called the customer for verification, but the line was busy. The bank blocked financial transactions from the device connected through the suspicious IP. The customer said, "At that time, I was on the phone with a voice phishing scammer impersonating my son," and added, "If the bank had not blocked it, I could have been scammed out of tens of millions of won," expressing relief.

# Earlier this month, a phishing scammer who withdrew 1 million won multiple times in installments from an ATM right after transferring funds from Bank A to Bank B was caught off guard when the withdrawal function suddenly stopped. The bank's system flagged the scammer's suspicious behavior, and the monitoring team called the customer but could not reach them, so the bank temporarily suspended the payments. The bold scammer then went directly to the branch to withdraw the remaining cash, but since the monitoring team had already contacted the branch, the phishing crime impersonating a prosecutor was detected on-site.

AI-based abnormal transaction detection systems (FDS) developed by domestic commercial banks are proving effective in preventing financial crimes. After President-elect Yoon Seok-yeol pledged to "strictly enforce laws against phishing" and strengthen the responsibilities of financial companies as part of his campaign promises, banks are also stepping up their responses. The Presidential Transition Committee and the Financial Supervisory Service have identified mandating the establishment of FDS as a top priority.

FDS refers to an AI system that detects transaction types that are unusual compared to normal patterns or those with a high incidence of electronic financial accidents, alerts customers, and prevents crimes. When abnormal financial transactions occur, banks conduct additional identity verification through an automated phone response system (ARS) and customer service representatives.

A Woori Bank official said, "If a transfer transaction occurs from a device being used for the first time via smartphone or PC, or if multiple transfers are made from the same account within a short period, the FDS detects it," adding, "It uses deep learning to analyze patterns in real time to precisely detect suspicious phishing transactions." Woori Bank led the way by integrating AI into FDS, followed by Kookmin Bank and Hana Bank, and Shinhan Bank plans to complete its advanced system next month.

AI-based abnormal behavior detection ATMs have also been introduced. A Shinhan Bank official explained, "This service detects and warns customers with cautionary messages when it observes suspicious behaviors similar to those found in numerous voice phishing data, such as customers talking on their phones during ATM transactions or wearing sunglasses or hats," adding, "It is a measure aimed at senior customers, who are primary targets of voice phishing."

Woori Bank also plans to launch AI abnormal behavior detection ATMs in the first half of the year. According to the Financial Supervisory Service, voice phishing damages have decreased from 443.9 billion won in 2018, 672 billion won in 2019, 235.3 billion won in 2020, to 84.5 billion won in the first half of last year, but the methods have become more diverse and sophisticated.