One-Class Adversarial Nets for Fraud Detection
This addresses fraud detection in online applications like social networks or e-commerce where malicious user records are scarce, offering a practical solution for real-world scenarios.
The paper tackled fraud detection when only benign user data is available by developing one-class adversarial nets (OCAN), which uses an LSTM-Autoencoder and a complementary GAN to learn representations and detect malicious users, achieving performance comparable to models requiring both benign and malicious data.
Many online applications, such as online social networks or knowledge bases, are often attacked by malicious users who commit different types of actions such as vandalism on Wikipedia or fraudulent reviews on eBay. Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users. However, in practice, there are often no or very few records of malicious users. In this paper, we develop one-class adversarial nets (OCAN) for fraud detection using training data with only benign users. OCAN first uses LSTM-Autoencoder to learn the representations of benign users from their sequences of online activities. It then detects malicious users by training a discriminator with a complementary GAN model that is different from the regular GAN model. Experimental results show that our OCAN outperforms the state-of-the-art one-class classification models and achieves comparable performance with the latest multi-source LSTM model that requires both benign and malicious users in the training phase.