Framework GNN-AID: Graph Neural Network Analysis Interpretation and Defense
Kirill Lukyanov, Mikhail Drobyshevskiy, Georgii Sazonov, Mikhail Soloviov, Ilya Makarov
TL;DR
GNN-AID tackles the gap in Trusted AI for graph data by delivering an integrated, open-source framework that combines interpretation, attacks, and defenses for Graph Neural Networks. Built on PyTorch-Geometric, it provides a modular pipeline, a no-code web frontend, and MLOps support to enable reproducible experimentation and rapid extension. The paper details a broad suite of implemented interpretation methods (e.g., GNNExplainer, SubgraphX, ProtGNN), attack types (e.g., Nettack, PGD, MetaAttack), and defenses (e.g., Adversarial Training, Gradient Regularization, JaccardDefense), and demonstrates through a case study on Cora that defenses can interact and sometimes conflict, highlighting the complexity of securing graph models. The work emphasizes practical impact for researchers and developers by enabling comprehensive graph-specific trust workflows and points to future work expanding attack/defense coverage and privacy-oriented capabilities.
Abstract
The growing need for Trusted AI (TAI) highlights the importance of interpretability and robustness in machine learning models. However, many existing tools overlook graph data and rarely combine these two aspects into a single solution. Graph Neural Networks (GNNs) have become a popular approach, achieving top results across various tasks. We introduce GNN-AID (Graph Neural Network Analysis, Interpretation, and Defense), an open-source framework designed for graph data to address this gap. Built as a Python library, GNN-AID supports advanced trust methods and architectural layers, allowing users to analyze graph datasets and GNN behavior using attacks, defenses, and interpretability methods. GNN-AID is built on PyTorch-Geometric, offering preloaded datasets, models, and support for any GNNs through customizable interfaces. It also includes a web interface with tools for graph visualization and no-code features like an interactive model builder, simplifying the exploration and analysis of GNNs. The framework also supports MLOps techniques, ensuring reproducibility and result versioning to track and revisit analyses efficiently. GNN-AID is a flexible tool for developers and researchers. It helps developers create, analyze, and customize graph models, while also providing access to prebuilt datasets and models for quick experimentation. Researchers can use the framework to explore advanced topics on the relationship between interpretability and robustness, test defense strategies, and combine methods to protect against different types of attacks. We also show how defenses against evasion and poisoning attacks can conflict when applied to graph data, highlighting the complex connections between defense strategies. GNN-AID is available at \href{https://github.com/ispras/GNN-AID}{github.com/ispras/GNN-AID}