Multi-View Graph Anomaly Detection Robustness Under Adversarial Perturbations

This report synthesises findings from 11 peer-reviewed papers addressing the following research question: How robust are multi-view graph anomaly detection frameworks with view dropout to adversarial perturbations (e.g., edge or node manipulations) compared to single-view methods, as evaluated by the. Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How robust are multi-view graph anomaly detection frameworks with view dropout to adversarial perturbations (e.g., edge or node manipulations) compared to single-view methods, as evaluated by the drop in detection performance (AUC-ROC, precision-recall) on perturbed graphs (e.g., using methods like Nettack or Metattack)?

Autonomous literature synthesis. Automated review score: 8.8/10. Full text and citation available at Assignee Research.