Building a Robust Mobile Payment Fraud Detection System with Adversarial Examples
Simon Delecourt, Li Qing Guo · 2019
Mobile payment is becoming a major payment method in many countries. However, the rate of payment fraud with mobile is higher than with credit card. One potential reason is that mobile data is easier to be modified than credit card data by fraudsters, which degrades our data-driven fraud detection system. Supervised learning methods are pervasively used in fraud detection. However, these supervised learning methods used in fraud detection have traditionally been developed following the assumption that the environment is benign; there are no adversaries trying to evade fraud detection system. In this paper, we took potential reactions of fraudsters into consideration to build a robust mobile fraud detection system using adversarial examples. Experimental results showed that the performance of our proposed method was improved in both benign and adversarial environments.