Multi-View vs. Single-View Graph Anomaly Detection Under Adversarial Perturbations

This report synthesises findings from 8 peer-reviewed papers addressing the following research question: How does the performance of multi-view graph anomaly detection models compare to single-view models when evaluated on adversarially perturbed graphs using metrics like AUC-ROC and precision-recall. A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard methodology has a serious flaw - virtually all of the defenses are evaluated against non-adaptive. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the performance of multi-view graph anomaly detection models compare to single-view models when evaluated on adversarially perturbed graphs using metrics like AUC-ROC and precision-recall under Nettack attacks?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.