arXiv research

Survey of graph adversarial learning tasks and their attacks and defenses.

New method improves graph representations against adversarial attacks.

Pro-GNN defends graph neural networks from adversarial attacks by learning graph structure.

Paper shows how to hide individuals in graphs to fool community detection models.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding dis…

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the laten…

Graph deep learning models, such as graph convolutional networks (GCN) achieve remarkable performance for tasks on graph data. Similar to other types of deep models, graph deep learning models often suffer from adversarial attacks. However, compared with non-graph data, the discrete features, graph connections and diff…

APGE protects graph node representations from inference attacks.

Bayesian optimisation method targets graph classification models against adversarial attacks.

New principle controls graph-informed adversarial discrepancies.

AdvImmune improves certifiable robustness of GNNs against adversarial attacks.

Graphs can be fooled by small edge changes, but this work protects them.

Graph Information Bottleneck (GIB) optimizes graph representations for robustness against adversarial attacks.

Graph neural network (GNN), as a powerful representation learning model on graph data, attracts much attention across various disciplines. However, recent studies show that GNN is vulnerable to adversarial attacks. How to make GNN more robust? What are the key vulnerabilities in GNN? How to address the vulnerabilities …

Real-world graph applications, such as advertisements and product recommendations make profits based on accurately classify the label of the nodes. However, in such scenarios, there are high incentives for the adversaries to attack such graph to reduce the node classification performance. Previous work on graph adversa…

Deep learning models for graphs have achieved strong performance for the task of node classification. Despite their proliferation, currently there is no study of their robustness to adversarial attacks. Yet, in domains where they are likely to be used, e.g. the web, adversaries are common. Can deep learning models for …

This paper explores vulnerabilities in hierarchical graph pooling neural networks for graph classification.

Adversarial training improves graph autoencoder generalization.

Recent methods for generating novel molecules use graph representations of molecules and employ various forms of graph convolutional neural networks for inference. However, training requires solving an expensive graph isomorphism problem, which previous approaches do not address or solve only approximately. In this wor…

New algorithm finds corrupted vertices in graphs with few queries.

We derive upper and lower bounds for the policy regret of $T$-round online learning problems with graph-structured feedback, where the adversary is nonoblivious but assumed to have a bounded memory. We obtain upper bounds of $\widetilde O(T^{2/3})$ and $\widetilde O(T^{3/4})$ for strongly-observable and weakly-observab…

Paper defends sensitive attributes in GNNs from inference attacks.

Indirect attacks can fool graph classifiers even with poisoned neighbors.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack an…

UAG defends GNNs against adversarial attacks by quantifying and explaining uncertainties.

New minimax optimal learner for robust predictors against adversarial examples.

DefenseVGAE defends graph neural networks against adversarial attacks.

With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, most of the current works perform the attack in a white-box fashion: they n…

Study examines unsupervised and graph-based methods for anomaly detection in IoBT, outperformed by supervised stacking ensemble.

Generative model for inferring graph from time series data.

Active learning (AL) on attributed graphs has received increasing attention with the prevalence of graph-structured data. Although AL has been widely studied for alleviating label sparsity issues with the conventional non-related data, how to make it effective over attributed graphs remains an open research question. E…

IDGL learns better graph structure and embeddings iteratively.

Deep learning on graph structures has shown exciting results in various applications. However, few attentions have been paid to the robustness of such models, in contrast to numerous research work for image or text adversarial attack and defense. In this paper, we focus on the adversarial attacks that fool the model by…

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (\eg articles with citation link tend to be in the same class), graph neural networks could be more sensiti…

Computer-aided breast cancer diagnosis in mammography is limited by inadequate data and the similarity between benign and cancerous masses. To address this, we propose a signed graph regularized deep neural network with adversarial augmentation, named \textsc{DiagNet}. Firstly, we use adversarial learning to generate p…

The paper examines how neural network topology affects adversarial robustness.

The effectiveness of Graph Convolutional Networks (GCNs) has been demonstrated in a wide range of graph-based machine learning tasks. However, the update of parameters in GCNs is only from labeled nodes, lacking the utilization of unlabeled data. In this paper, we apply Virtual Adversarial Training (VAT), an adversaria…

This paper examines how graph topology affects adversarial attacks on vertex classification.

Graph attacks can be successful with just a few bad nodes.

The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversari…

Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and d…

Adversarial CBO optimizes under interventions by adversaries and non-stationarities.

Graph neural networks are vulnerable to adversarial attacks by manipulating graph structure.

RIA method improves OoD generalization for covariate shift.

Paper provides robustness bounds for GNNs against adversarial attacks.

Generative model predicts multiple brain graphs from one, preserving topology.

Paper improves robustness of GNNs against adversarial attacks.

DeepRobust is a PyTorch library for adversarial attacks and defenses.