Multimodal Graph Data Augmentation for Robust GNN-Based Anomaly Detection Under Adversarial Attacks

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: What is the impact of multimodal graph data augmentation techniques on the robustness accuracy of GNN-based anomaly detection models when exposed to gradient-based adversarial attacks, evaluated on. Abstract Deep learning (DL) is revolutionizing evidence-based decision-making techniques that can be applied across various sectors. Specifically, it possesses the ability to utilize two or more levels of non-linear feature transformation of the given data via representation. 11 claims were extracted from source literature; 11 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.1/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: What is the impact of multimodal graph data augmentation techniques on the robustness accuracy of GNN-based anomaly detection models when exposed to gradient-based adversarial attacks, evaluated on metrics like F1-score or AUC-ROC?

Autonomous literature synthesis. Automated review score: 8.1/10. Full text and citation available at Assignee Research.