Action Sequence Augmentation for Early Graph-based Anomaly Detection

TL;DR

This paper introduces Eland, a framework that enhances early graph-based anomaly detection by augmenting action sequences, leading to better detection performance with limited user data.

Contribution

Eland is the first to combine action sequence augmentation with graph-based anomaly detection for early detection, improving accuracy with less observed data.

Findings

Eland improves detection performance by up to 15% AUC at early stages.

Action sequence augmentation enhances existing graph-based methods.

Eland performs well across multiple real-world datasets.

Abstract

The proliferation of web platforms has created incentives for online abuse. Many graph-based anomaly detection techniques are proposed to identify the suspicious accounts and behaviors. However, most of them detect the anomalies once the users have performed many such behaviors. Their performance is substantially hindered when the users' observed data is limited at an early stage, which needs to be improved to minimize financial loss. In this work, we propose Eland, a novel framework that uses action sequence augmentation for early anomaly detection. Eland utilizes a sequence predictor to predict next actions of every user and exploits the mutual enhancement between action sequence augmentation and user-action graph anomaly detection. Experiments on three real-world datasets show that Eland improves the performance of a variety of graph-based anomaly detection methods. With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.