CausalFD: causal invariance-based fraud detection against camouflaged preference

Fraudsters engage in diverse patterns and deceptive interactions, allowing them to move effortlessly within online networks. However, current fraud detection methods heavily rely on correlated experiences and often face challenges in adapting to changing fraud patterns. To solve this problem, our paper introduces a fraud detection method called CausalFD. It includes a mechanism that learns the invariant preference behind evolving camouflaged preference as fraud patterns change. Specifically, we first introduce the concept of camouflaged preference in fraud detection to reveal the importance of identifying fraudster behavior variation and invariance for aiding downstream task inference. Next, we design a module called neighborhood heterophily perception (NHP) to measure the level of heterophily between a node and its neighbors. This helps in understanding the node’s surroundings to identify fraud patterns and establish environmental conditions for causal inference. Lastly, we design the preference invariance mining (PIM) module to uncover potential causal relationships among users. This module analyzes user associations using the causal inference mechanism to identify consistent user preferences. The combination of both methods enables the identification of the fraudster’s motives even amidst changing fraud patterns. We conducted extensive experiments on two widely used fraud datasets, and the results demonstrate that our model exhibits excellent capabilities in fraud detection.