CoATA-Enhanced GNN Robustness Against Adversarial Attacks on Cora and Citeseer

This report synthesises findings from 4 peer-reviewed papers addressing the following research question: How does the robustness of GNNs trained with CoATA's co-augmentation perform under adversarial attacks compared to those trained with single-dimensional augmentation, as measured by accuracy. This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g.. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.7/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the robustness of GNNs trained with CoATA's co-augmentation perform under adversarial attacks compared to those trained with single-dimensional augmentation, as measured by accuracy degradation on perturbed versions of the Cora or Citeseer datasets?

Autonomous literature synthesis. Automated review score: 8.7/10. Full text and citation available at Assignee Research.