Robust Fraud Detection via Supervised Contrastive Learning

TL;DR

This paper introduces ConRo, a supervised contrastive learning framework designed to improve fraud detection in scenarios with limited malicious session data, by generating diverse malicious samples and enhancing model generalization.

Contribution

The paper presents a novel contrastive learning approach with data augmentation for open-set fraud detection, addressing the challenge of limited malicious session diversity.

Findings

ConRo outperforms state-of-the-art baselines on benchmark datasets.

Data augmentation enhances the diversity of malicious sessions.

Supervised contrastive learning improves generalization to unseen malicious sessions.

Abstract

Deep learning models have recently become popular for detecting malicious user activity sessions in computing platforms. In many real-world scenarios, only a few labeled malicious and a large amount of normal sessions are available. These few labeled malicious sessions usually do not cover the entire diversity of all possible malicious sessions. In many scenarios, possible malicious sessions can be highly diverse. As a consequence, learned session representations of deep learning models can become ineffective in achieving a good generalization performance for unseen malicious sessions. To tackle this open-set fraud detection challenge, we propose a robust supervised contrastive learning based framework called ConRo, which specifically operates in the scenario where only a few malicious sessions having limited diversity is available. ConRo applies an effective data augmentation strategy to generate diverse potential malicious sessions. By employing these generated and available training set sessions, ConRo derives separable representations w.r.t open-set fraud detection task by leveraging supervised contrastive learning. We empirically evaluate our ConRo framework and other state-of-the-art baselines on benchmark datasets. Our ConRo framework demonstrates noticeable performance improvement over state-of-the-art baselines.