mlsanityData to 7 Oct 2026

CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection

arXiv 2605.20032 ↗First posted 19 May 2026cs.LG cs.MMcited by 3

Not on the map. Why?

Abstract (arXiv)

Text-attributed graph fraud detection (TAGFD) plays a critical role in preventing fraudulent activities on online social and e-commerce platforms. However, to evade detection, fraudsters continuously evolve their camouflaging strategies by deliberately mimicking textual responses of benign users, thereby concealing their malicious purposes. This phenomenon, referred to as semantic camouflage, fundamentally undermines commonly relied assumptions on how structural and attribute cues can be exploited to identify fraudsters, and makes it difficult to spot fraudsters with unsupervised TAGFD. To bridge the gaps, we propose a Case-Adaptive Multi-cue Expert fRAmework (CAMERA) for unsupervised TAGFD. CAMERA employs an ego-decoupled mixture-of-experts architecture, where each expert specializes in modeling a distinct type of fraud-indicative cue. A context-informed gating model is introduced to jointly consider the ego node representation and its local neighborhood context for adaptive integration of cues learned by different experts. Furthermore, CAMERA leverages the inherent rarity of fraudsters to support unsupervised one-class learning with expert-level objectives that encourage modeling dominant benign patterns, thereby enabling reliable unsupervised detection of camouflaged fraudsters. Experiments on 4 challenging datasets show that CAMERA consistently outperforms competitors, showing its effectiveness against semantically camouflaged fraudsters. Code available at https://github.com/CampanulaBells/CAMERA

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 19 May 2026.

Builds on

34 of 48 references.

References · 34

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  2. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  3. 2021BASE Layers: Simplifying Training of Large, Sparse Modelscited by 315
  4. 2020Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsterscited by 248
  5. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  6. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  7. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 175
  8. 2021DEMix Layers: Disentangling Domains for Modular Language Modelingcited by 130
  9. 2013From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviewscited by 107
  10. 2023GAD-NR: Graph Anomaly Detection via Neighborhood Reconstructioncited by 44
  11. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  12. 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Modelscited by 36
22 more
  1. 2023Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizercited by 28
  2. 2023PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detectioncited by 25
  3. 2025A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detectioncited by 24
  4. 2023ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detectioncited by 23
  5. 2025SpaceGNN: Multi-Space Graph Neural Network for Node Anomaly Detection with Extremely Limited Labelscited by 17
  6. 2022Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Methodcited by 15
  7. 2025Bisecle: Binding and Separation in Continual Learning for Video Language Understandingcited by 13
  8. 2025A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Modelscited by 13
  9. 2026DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learningcited by 13
  10. 2023Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detectioncited by 12
  11. 2025Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Timecited by 12
  12. 2025DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMscited by 11
  13. 2025FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detectioncited by 10
  14. 2025Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detectioncited by 8
  15. 2026From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detectioncited by 8
  16. 2024GuARD: Effective Anomaly Detection through a Text-Rich and Graph-Informed Language Modelcited by 6
  17. 2025Out-of-Distribution Detection on Graphs: A Surveycited by 6
  18. 2026FedCIGAR: A Personalized Reconstruction Approach for Federated Graph-level Anomaly Detectioncited by 6
  19. 2026Towards One-for-All Anomaly Detection for Tabular Datacited by 5
  20. 2025Text-Attributed Graph Anomaly Detection via Multi-Scale Cross- and Uni-Modal Contrastive Learningcited by 4
  21. 2025Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detectioncited by 4
  22. 2025Court of LLMs: Evidence-Augmented Generation via Multi-LLM Collaboration for Text-Attributed Graph Anomaly Detectioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Towards Anomaly Detection on Relational Datacited by 4
  2. 2026SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detectioncited by 0
  3. 2026DiFA: Dual Evidence Fusion and Aggregation for Token-Level Text Anomaly Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection
  2. 2025SCFCRC: Simultaneously Counteract Feature Camouflage and Relation Camouflage for Fraud Detection
  3. 2026Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
  4. 2025LLM-Powered Text-Attributed Graph Anomaly Detection via Retrieval-Augmented Reasoning
  5. 2026Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation
  6. 2026THEMIS: Towards Holistic Evaluation of MLLMs for Scientific Paper Fraud Forensics
  7. 2025HAMLET-FFD: Hierarchical Adaptive Multi-modal Learning Embeddings Transformation for Face Forgery Detection
  8. 2025Identity-Aware Vision-Language Model for Explainable Face Forgery Detection