Spotting Collective Behaviour of Online Frauds in Customer Reviews

Dhawan, Sarthika; Gangireddy, Siva Charan Reddy; Kumar, S. Sampath; Chakraborty, Tanmoy

doi:10.24963/ijcai.2019/35

Cited by 31 publications

(8 citation statements)

References 9 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, where e ≥ 10. (7) It means that the RL converges in the recent ten epochs and indicates an optimal threshold p (l ) r is discovered. After the RL module terminates, the filtering thresholds are fixed as the optimal one until the convergence of GNN.…”

Section: 32mentioning

confidence: 99%

“…When the filtering threshold oscillates for several rounds, it reaches the terminal condition in Eq. (7). For different datasets, the proposed RL algorithm could adaptively find the optimal filtering thresholds.…”

Section: Rl Process Analysismentioning

confidence: 99%

“…Fraudsters disguise as regular users to bypass the anti-fraud system and disperse disinformation [44] or reap end-users' privacy [32]. To detect those fraudulent activities, graph-based methods have become an effective approach in both academic [7,21,38] and industrial communities [2,28,50]. Graphbased methods connect entities with different relations and reveal the suspiciousness of these entities at the graph level, since fraudsters with the same goal tend to connect with each other [1].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

Dou

Liu

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

262

160

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have been widely applied to fraud detection problems in recent years, revealing the suspiciousness of nodes by aggregating their neighborhood information via different relations. However, few prior works have noticed the camouflage behavior of fraudsters, which could hamper the performance of GNNbased fraud detectors during the aggregation process. In this paper, we introduce two types of camouflages based on recent empirical studies, i.e., the feature camouflage and the relation camouflage. Existing GNNs have not addressed these two camouflages, which results in their poor performance in fraud detection problems. Alternatively, we propose a new model named CAmouflage-REsistant GNN (CARE-GNN), to enhance the GNN aggregation process with three unique modules against camouflages. Concretely, we first devise a label-aware similarity measure to find informative neighboring nodes. Then, we leverage reinforcement learning (RL) to find the optimal amounts of neighbors to be selected. Finally, the selected neighbors across different relations are aggregated together. Comprehensive experiments on two real-world fraud datasets demonstrate the effectiveness of the RL algorithm. The proposed CARE-GNN also outperforms state-of-the-art GNNs and GNN-based fraud detectors. We integrate all GNN-based fraud detectors as an opensource toolbox 1. The CARE-GNN code and datasets are available at https://github.com/YingtongDou/CARE-GNN. CCS CONCEPTS • Security and privacy → Web application security; • Computing methodologies → Neural networks.

show abstract

Section: 32mentioning

confidence: 99%

Section: Rl Process Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters

Dou

Liu

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

262

160

View full text Add to dashboard Cite

show abstract

“…Wang et al [9] later introduce a new approach that decompose the entire reviewer graph into small fake reviewer groups by a minimum cut algorithm. Dhawan et al [17] propose DeFrauder that harnesses group indicators from behavior and graph features to discover and rank fake reviewer groups. However, they do not consider group-level and individuallevel features in a unified manner, ignoring the effectiveness of traditional features in group detection.…”

Section: A Fake Reviewer Detectionmentioning

confidence: 99%

“…It uses a density-based clustering approach[38] to extract candidate groups rather than deep approaches. Note that in our experiments we use vanilla ColluEagle without node prior.• DeFrauder by Dhawan et al[17] first uses group indicators to extract groups, and then performs graph embedding via node2vec[39] to calculate density-based spam scores. DeFrauder exploits only group features, ignoring individual-level ones.…”

mentioning

confidence: 99%

Fake Reviewer Group Detection in Online Review Systems

Chen¹,

Li²,

Yu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Online review systems are important components in influencing customers' purchase decisions. To manipulate a product's reputation, many stores hire large numbers of people to produce fake reviews to mislead customers. Previous methods tackle this problem by detecting malicious individuals, ignoring the fact that the spam activities are often formed in groups, where individuals work collectively to write fake reviews. Fake reviewer group detection, however, is more challenging due to the difficulties in capturing the underlying relationships in groups. In this work, we present an unsupervised and end-toend approach for fake reviewer group detection in online reviews. Specifically, our method can be summarized into two procedures. First, cohensive groups are detected with modularity-based graph convolutional networks. Then the suspiciousness of each group is measured by several anomaly indicators from both individual and group levels. The fake reviewer groups can be finally detected through suspiciousness. Extensive experiments are conducted on real-world datasets, and the results show that our proposed method is effective in detecting fake reviewer groups compared with the state-of-the-art baselines.

show abstract