Contractive Systems Improve Graph Neural Networks Against Adversarial Attacks
- URL: http://arxiv.org/abs/2311.06942v2
- Date: Thu, 20 Jun 2024 10:26:56 GMT
- Title: Contractive Systems Improve Graph Neural Networks Against Adversarial Attacks
- Authors: Moshe Eliasof, Davide Murari, Ferdia Sherry, Carola-Bibiane Schönlieb,
- Abstract summary: Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks.
Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversarial attacks.
This paper introduces an innovative approach to fortify GNNs against adversarial perturbations through the lens of contractive dynamical systems.
- Score: 12.856220339384269
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph Neural Networks (GNNs) have established themselves as a key component in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain susceptible to input perturbations in the form of adversarial attacks. This paper introduces an innovative approach to fortify GNNs against adversarial perturbations through the lens of contractive dynamical systems. Our method introduces graph neural layers based on differential equations with contractive properties, which, as we show, improve the robustness of GNNs. A distinctive feature of the proposed approach is the simultaneous learned evolution of both the node features and the adjacency matrix, yielding an intrinsic enhancement of model robustness to perturbations in the input features and the connectivity of the graph. We mathematically derive the underpinnings of our novel architecture and provide theoretical insights to reason about its expected behavior. We demonstrate the efficacy of our method through numerous real-world benchmarks, reading on par or improved performance compared to existing methods.
Related papers
- GNN-VPA: A Variance-Preserving Aggregation Strategy for Graph Neural
Networks [11.110435047801506]
We propose a variance-preserving aggregation function (VPA) that maintains expressivity, but yields improved forward and backward dynamics.
Our results could pave the way towards normalizer-free or self-normalizing GNNs.
arXiv Detail & Related papers (2024-03-07T18:52:27Z) - A Simple and Yet Fairly Effective Defense for Graph Neural Networks [18.140756786259615]
Graph Neural Networks (GNNs) have emerged as the dominant approach for machine learning on graph-structured data.
Existing defense methods against small adversarial perturbations suffer from high time complexity.
This paper introduces NoisyGNNs, a novel defense method that incorporates noise into the underlying model's architecture.
arXiv Detail & Related papers (2024-02-21T18:16:48Z) - HGAttack: Transferable Heterogeneous Graph Adversarial Attack [63.35560741500611]
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce.
This paper introduces HGAttack, the first dedicated gray box evasion attack method for heterogeneous graphs.
arXiv Detail & Related papers (2024-01-18T12:47:13Z) - Attentional Graph Neural Networks for Robust Massive Network
Localization [20.416879207269446]
Graph neural networks (GNNs) have emerged as a prominent tool for classification tasks in machine learning.
This paper integrates GNNs with attention mechanism to tackle a challenging nonlinear regression problem: network localization.
We first introduce a novel network localization method based on graph convolutional network (GCN), which exhibits exceptional precision even under severe non-line-of-sight (NLOS) conditions.
arXiv Detail & Related papers (2023-11-28T15:05:13Z) - Label Deconvolution for Node Representation Learning on Large-scale
Attributed Graphs against Learning Bias [75.44877675117749]
We propose an efficient label regularization technique, namely Label Deconvolution (LD), to alleviate the learning bias by a novel and highly scalable approximation to the inverse mapping of GNNs.
Experiments demonstrate LD significantly outperforms state-of-the-art methods on Open Graph datasets Benchmark.
arXiv Detail & Related papers (2023-09-26T13:09:43Z) - DEGREE: Decomposition Based Explanation For Graph Neural Networks [55.38873296761104]
We propose DEGREE to provide a faithful explanation for GNN predictions.
By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction.
We also design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods.
arXiv Detail & Related papers (2023-05-22T10:29:52Z) - Resisting Graph Adversarial Attack via Cooperative Homophilous
Augmentation [60.50994154879244]
Recent studies show that Graph Neural Networks are vulnerable and easily fooled by small perturbations.
In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack.
We propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model.
arXiv Detail & Related papers (2022-11-15T11:44:31Z) - Spiking Variational Graph Auto-Encoders for Efficient Graph
Representation Learning [10.65760757021534]
We propose an SNN-based deep generative method, namely the Spiking Variational Graph Auto-Encoders (S-VGAE) for efficient graph representation learning.
We conduct link prediction experiments on multiple benchmark graph datasets, and the results demonstrate that our model consumes significantly lower energy with the performances superior or comparable to other ANN- and SNN-based methods for graph representation learning.
arXiv Detail & Related papers (2022-10-24T12:54:41Z) - Relation Embedding based Graph Neural Networks for Handling
Heterogeneous Graph [58.99478502486377]
We propose a simple yet efficient framework to make the homogeneous GNNs have adequate ability to handle heterogeneous graphs.
Specifically, we propose Relation Embedding based Graph Neural Networks (RE-GNNs), which employ only one parameter per relation to embed the importance of edge type relations and self-loop connections.
arXiv Detail & Related papers (2022-09-23T05:24:18Z) - Graph Backdoor [53.70971502299977]
We present GTA, the first backdoor attack on graph neural networks (GNNs)
GTA departs in significant ways: it defines triggers as specific subgraphs, including both topological structures and descriptive features.
It can be instantiated for both transductive (e.g., node classification) and inductive (e.g., graph classification) tasks.
arXiv Detail & Related papers (2020-06-21T19:45:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.