Artificial Intelligence Will Detect Social Media Fraudsters
After the earthquakes described as the “disaster of the century”, TÜBİTAK BİLGEM researchers rolled up their sleeves after the increase in fraud attempts under the name of donations and aid on social media. An artificial intelligence has been developed that detects scams.
The system, which the researchers implemented in two days, was opened to the use of the Information Technologies and Communication Authority (BTK) and other relevant institutions.
The software, called “Fraud Detection with Twitter Data Analysis” and currently only working on Twitter, scans tweets containing keywords such as “AFAD”, “Kızılay”, “AKUT”, “AHBAP” to ensure that the IBANs in them belong to the relevant person. she’s making sure. suitable person. she’s making sure. relevant institutions. checks if it’s not.
Account numbers that are not authorized to collect aid are marked as “suspicious” by the software and shown to the user.
“WE OPENED ACCESS VIA WEB SERVICE”
İlknur Dönmez, who works as an expert researcher at BİLGEM, said that it was revealed that some malicious people on social media demanded that money be deposited to their account numbers by using the names of aid organizations.
Stating that he asked TÜBİTAK to make a program on the subject, Dönmez noted that they started to work quickly to identify Twitter posts containing IBANs that do not belong to official institutions, using keywords.
Explaining that they completed and delivered the program in 2 days with a team of 11 people, Dönmez said, “We opened it to external access via the web service. BTK enters the program and checks whether the tweets we marked as suspicious are really suspicious. It takes the necessary measures.” aforementioned.
IT WILL EXPAND FURTHER
Noting that the program evaluates both the text areas and the attached pictures together in tweets, Dönmez continued as follows:
“First of all, it converts images into text by passing them through optical scanning systems. Thus, it finds keywords such as AFAD, AKUT, Kızılay, AHBAP both in the text and in the image. It also extracts their IBANs, if any. Then it is checked whether these IBANs belong to the relevant institutions. , “If there is a conflict, it is flagged as suspicious by the system. Thus, the program allows the user to see suspicious tweets. 1 million 500 thousand tweets containing keywords were scanned. 1,000 of these have been flagged as suspects.”
Stating that the program only works on Twitter for now, but they aim to reach wider social media areas in the future, Dönmez added that they plan to develop the program with the notifications from BTK.