Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to Any-Layer Graph Neural Networks via Influence Function
This addresses the vulnerability of GNNs to adversarial attacks in graph data, offering a practical and scalable solution for security applications, though it is incremental as it builds on existing evasion attack concepts.
The paper tackles the problem of graph evasion attacks on graph neural networks (GNNs) by proposing an influence-based black-box attack method that is efficient, direct, and applicable to any-layer GNNs, achieving comparable performance to state-of-the-art white-box attacks with a 5-50x speedup for two-layer GNNs.
Graph neural network (GNN), the mainstream method to learn on graph data, is vulnerable to graph evasion attacks, where an attacker slightly perturbing the graph structure can fool trained GNN models. Existing work has at least one of the following drawbacks: 1) limited to directly attack two-layer GNNs; 2) inefficient; and 3) impractical, as they need to know full or part of GNN model parameters. We address the above drawbacks and propose an influence-based \emph{efficient, direct, and restricted black-box} evasion attack to \emph{any-layer} GNNs. Specifically, we first introduce two influence functions, i.e., feature-label influence and label influence, that are defined on GNNs and label propagation (LP), respectively. Then we observe that GNNs and LP are strongly connected in terms of our defined influences. Based on this, we can then reformulate the evasion attack to GNNs as calculating label influence on LP, which is \emph{inherently} applicable to any-layer GNNs, while no need to know information about the internal GNN model. Finally, we propose an efficient algorithm to calculate label influence. Experimental results on various graph datasets show that, compared to state-of-the-art white-box attacks, our attack can achieve comparable attack performance, but has a 5-50x speedup when attacking two-layer GNNs. Moreover, our attack is effective to attack multi-layer GNNs\footnote{Source code and full version is in the link: \url{https://github.com/ventr1c/InfAttack}}.