2025年01月02日

A binary classification problem where the attacker’s goal is to identify the true positives from the false positives (scammed vs cannot be scammed). However, it is very difficult to build a classifier since that requires data from actual victims. "Nigerian Scam" is used because this filters potential victims from the ones who doesn’t fall for scams. Victims who are oblivious to scams will be marked as viable targets for the scammers.