Related papers: Graph Neural Network Explanations are Fragile

Graph Neural Network Explanations are Fragile

URL: http://arxiv.org/abs/2406.03193v1
Date: Wed, 5 Jun 2024 12:23:02 GMT
Title: Graph Neural Network Explanations are Fragile
Authors: Jiate Li, Meng Pang, Yun Dong, Jinyuan Jia, Binghui Wang,
Abstract summary: We take the first step to study GNN explainers under adversarial attack. We find that an adversary slightly perturbing graph structure can ensure GNN model makes correct predictions, but the GNN explainer yields a drastically different explanation on the perturbed graph.
Score: 39.9987140075811
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Explainable Graph Neural Network (GNN) has emerged recently to foster the trust of using GNNs. Existing GNN explainers are developed from various perspectives to enhance the explanation performance. We take the first step to study GNN explainers under adversarial attack--We found that an adversary slightly perturbing graph structure can ensure GNN model makes correct predictions, but the GNN explainer yields a drastically different explanation on the perturbed graph. Specifically, we first formulate the attack problem under a practical threat model (i.e., the adversary has limited knowledge about the GNN explainer and a restricted perturbation budget). We then design two methods (i.e., one is loss-based and the other is deduction-based) to realize the attack. We evaluate our attacks on various GNN explainers and the results show these explainers are fragile.

Related papers

Global Graph Counterfactual Explanation: A Subgraph Mapping Approach [54.42907350881448]
Graph Neural Networks (GNNs) have been widely deployed in various real-world applications. Counterfactual explanation aims to find minimum perturbations on input graphs that change the GNN predictions. We propose GlobalGCE, a novel global-level graph counterfactual explanation method.
arXiv Detail & Related papers (2024-10-25T21:39:05Z)
Explainable Graph Neural Networks Under Fire [69.15708723429307]
Graph neural networks (GNNs) usually lack interpretability due to their complex computational behavior and the abstract nature of graphs. Most GNN explanation methods work in a post-hoc manner and provide explanations in the form of a small subset of important edges and/or nodes. In this paper we demonstrate that these explanations can unfortunately not be trusted, as common GNN explanation methods turn out to be highly susceptible to adversarial perturbations.
arXiv Detail & Related papers (2024-06-10T16:09:16Z)
Link Stealing Attacks Against Inductive Graph Neural Networks [60.931106032824275]
A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Previous work has shown that transductive GNNs are vulnerable to a series of privacy attacks. This paper conducts a comprehensive privacy analysis of inductive GNNs through the lens of link stealing attacks.
arXiv Detail & Related papers (2024-05-09T14:03:52Z)
On Consistency in Graph Neural Network Interpretation [34.25952902469481]
Instance-level GNN explanation aims to discover critical input elements, like nodes or edges, that the target GNN relies upon for making predictions. Various algorithms are proposed, but most of them formalize this task by searching the minimal subgraph. We propose a simple yet effective countermeasure by aligning embeddings.
arXiv Detail & Related papers (2022-05-27T02:58:07Z)
Explainability in Graph Neural Networks: An Experimental Survey [12.440636971075977]
Graph neural networks (GNNs) have been extensively developed for graph representation learning. GNNs suffer from the black-box problem as people cannot understand the mechanism underlying them. Several GNN explainability methods have been proposed to explain the decisions made by GNNs.
arXiv Detail & Related papers (2022-03-17T11:25:41Z)
Jointly Attacking Graph Neural Network and its Explanations [50.231829335996814]
Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks. Recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs. We propose a novel attack framework (GEAttack) which can attack both a GNN model and its explanations by simultaneously exploiting their vulnerabilities.
arXiv Detail & Related papers (2021-08-07T07:44:33Z)
Generative Causal Explanations for Graph Neural Networks [39.60333255875979]
Gem is a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. It achieves a relative increase of the explanation accuracy by up to $30%$ and speeds up the explanation process by up to $110times$ as compared to its state-of-the-art alternatives.
arXiv Detail & Related papers (2021-04-14T06:22:21Z)
Graph Structure Learning for Robust Graph Neural Networks [63.04935468644495]
Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. Recent studies show that GNNs are vulnerable to carefully-crafted perturbations, called adversarial attacks. We propose a general framework Pro-GNN, which can jointly learn a structural graph and a robust graph neural network model.
arXiv Detail & Related papers (2020-05-20T17:07:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.