相关论文: Adversarial Attacks on Node Embeddings via Graph P…

Graph neural network (GNN) explanations have largely been facilitated through post-hoc introspection. While this has been deemed successful, many post-hoc explanation methods have been shown to fail in capturing a model's learned…

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

A cursory reading of the literature suggests that we have made a lot of progress in designing effective adversarial defenses for Graph Neural Networks (GNNs). Yet, the standard methodology has a serious flaw - virtually all of the defenses…

Despite the widespread use of Knowledge Graph Embeddings (KGE), little is known about the security vulnerabilities that might disrupt their intended behaviour. We study data poisoning attacks against KGE models for link prediction. These…

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Graph Neural Networks (GNNs) have significantly advanced various downstream graph-relevant tasks, encompassing recommender systems, molecular structure prediction, social media analysis, etc. Despite the boosts of GNN, recent research has…

We consider availability data poisoning attacks, where an adversary aims to degrade the overall test accuracy of a machine learning model by crafting small perturbations to its training data. Existing poisoning strategies can achieve the…

The existing research on robust Graph Neural Networks (GNNs) fails to acknowledge the significance of directed graphs in providing rich information about networks' inherent structure. This work presents the first investigation into the…

Graphs representation learning has been a very active research area in recent years. The goal of graph representation learning is to generate graph representation vectors that capture the structure and features of large graphs accurately.…

In this work, we propose the first backdoor attack to graph neural networks (GNN). Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification. In our backdoor attack, a GNN classifier predicts an…

Complex networks represented as node adjacency matrices constrains the application of machine learning and parallel algorithms. To address this limitation, network embedding (i.e., graph representation) has been intensively studied to learn…

The prominent success of neural networks, mainly in computer vision tasks, is increasingly shadowed by their sensitivity to small, barely perceivable adversarial perturbations in image input. In this work, we aim at explaining this…

Deep learning solutions are instrumental in cybersecurity, harnessing their ability to analyze vast datasets, identify complex patterns, and detect anomalies. However, malevolent actors can exploit these capabilities to orchestrate…

Recently a variety of methods have been developed to encode graphs into low-dimensional vectors that can be easily exploited by machine learning algorithms. The majority of these methods start by embedding the graph nodes into a…

We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In particular, we use adversarial robustness as a tool to uncover…

Computing latent representations for graph-structured data is an ubiquitous learning task in many industrial and academic applications ranging from molecule synthetization to social network analysis and recommender systems. Knowledge graphs…

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to…

Graph Neural Networks (GNNs) have demonstrated remarkable performance across a spectrum of graph-related tasks, however concerns persist regarding their vulnerability to adversarial perturbations. While prevailing defense strategies focus…

Many real-world data comes in the form of graphs, such as social networks and protein structure. To fully utilize the information contained in graph data, a new family of machine learning (ML) models, namely graph neural networks (GNNs),…

It has been demonstrated that adversarial graphs, i.e., graphs with imperceptible perturbations added, can cause deep graph models to fail on node/graph classification tasks. In this paper, we extend adversarial graphs to the problem of…