Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

TL;DR

This paper emphasizes the importance of standardized, fair evaluation protocols for adversarial attacks and defenses on Graph Neural Networks, revealing significant performance variations under different settings.

Contribution

It provides a comprehensive benchmark re-evaluating seven attacks and eight defenses across multiple datasets using a unified framework, highlighting overlooked factors affecting attack effectiveness.

Findings

Substantial differences in attack performance under fair evaluation.

Target node selection and training process significantly impact attack success.

Standardized evaluation protocols are urgently needed in adversarial GNN research.

Abstract

Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes. While a rigorous evaluation of these adversarial methods is necessary to understand the robustness of GNNs in real-world applications, we posit that many works in the literature do not share the same experimental settings, leading to ambiguous and potentially contradictory scientific conclusions. In this benchmark, we demonstrate the importance of adopting fair, robust, and standardized evaluation protocols in adversarial GNN research. We perform a comprehensive re-evaluation of seven widely used attacks and eight recent defenses under both poisoning and evasion scenarios, across six popular graph datasets. Our study spans over 453,000 experiments conducted within a unified framework. We observe substantial differences in adversarial attack performance when evaluated under a fair and robust procedure. Our findings reveal that previously overlooked factors, such as target node selection and the training process of the attacked model, have a profound impact on attack effectiveness, to the extent of completely distorting performance insights. These results underscore the urgent need for standardized evaluations in adversarial graph machine learning.