When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning

TL;DR

This paper introduces a novel topological layer for graph neural networks that enhances robustness against adversarial attacks by focusing on salient shape features using persistent homology and witness complexes.

Contribution

It proposes the Witness Graph Topological Layer (WGTL), integrating local and global topological features with stability guarantees, improving GNN robustness against adversarial perturbations.

Findings

WGTL boosts GNN robustness across multiple datasets.

The method provides stability guarantees for topological encodings.

Integration with existing GNNs and defenses enhances adversarial resilience.

Abstract

Capitalizing on the intuitive premise that shape characteristics are more robust to perturbations, we bridge adversarial graph learning with the emerging tools from computational topology, namely, persistent homology representations of graphs. We introduce the concept of witness complex to adversarial analysis on graphs, which allows us to focus only on the salient shape characteristics of graphs, yielded by the subset of the most essential nodes (i.e., landmarks), with minimal loss of topological information on the whole graph. The remaining nodes are then used as witnesses, governing which higher-order graph substructures are incorporated into the learning process. Armed with the witness mechanism, we design Witness Graph Topological Layer (WGTL), which systematically integrates both local and global topological graph feature representations, the impact of which is, in turn, automatically controlled by the robust regularized topological loss. Given the attacker's budget, we derive the important stability guarantees of both local and global topology encodings and the associated robust topological loss. We illustrate the versatility and efficiency of WGTL by its integration with five GNNs and three existing non-topological defense mechanisms. Our extensive experiments across six datasets demonstrate that WGTL boosts the robustness of GNNs across a range of perturbations and against a range of adversarial attacks. Our datasets and source codes are available at https://github.com/toggled/WGTL.