相关论文: Private Graph Extraction via Feature Explanations

Over the past few years, federated learning has become widely used in various classical machine learning fields because of its collaborative ability to train data from multiple sources without compromising privacy. However, in the area of…

Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…

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…

Recent research has revealed that Graph Neural Networks (GNNs) are susceptible to adversarial attacks targeting the graph structure. A malicious attacker can manipulate a limited number of edges, given the training labels, to impair the…

Graph unlearning emerges as a crucial advancement in the pursuit of responsible AI, providing the means to remove sensitive data traces from trained models, thereby upholding the \textit{right to be forgotten}. It is evident that graph…

With the increasing popularity of graph neural networks (GNNs) in several sensitive applications like healthcare and medicine, concerns have been raised over the privacy aspects of trained GNNs. More notably, GNNs are vulnerable to privacy…

Graph Neural Networks (GNNs) have become indispensable tools for learning from graph structured data, catering to various applications such as social network analysis and fraud detection for financial services. At the heart of these…

Deep neural networks are increasingly deployed for scene analytics, including to evaluate the attention and reaction of people exposed to out-of-home advertisements. However, the features extracted by a deep neural network that was trained…

Deep neural networks (DNNs) have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that DNNs are vulnerable to…

Along with the advent of deep neural networks came various methods of exploitation, such as fooling the classifier or contaminating its training data. Another such attack is known as model extraction, where provided API access to some black…

The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security…

Graphs are the dominant formalism for modeling multi-agent systems. The algebraic connectivity of a graph is particularly important because it provides the convergence rates of consensus algorithms that underlie many multi-agent control and…

Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certain circumstances, is possible. In this work, we analyse such…

Although recent network representation learning (NRL) works in text-attributed networks demonstrated superior performance for various graph inference tasks, learning network representations could always raise privacy concerns when nodes…

Despite the recent progress in Graph Neural Networks (GNNs), it remains challenging to explain the predictions made by GNNs. Existing explanation methods mainly focus on post-hoc explanations where another explanatory model is employed to…

Graph Neural Networks (GNNs) are widely used and deployed for graph-based prediction tasks. However, as good as GNNs are for learning graph data, they also come with the risk of privacy leakage. For instance, an attacker can run carefully…

Graph Neural Networks (GNNs) have boosted the performance of many graph related tasks such as node classification and graph classification. Recent researches show that graph neural networks are vulnerable to adversarial attacks, which…

Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAs), given their ability to learn joint representation from features and edges among nodes in graph data. To prevent privacy leakages in GNNs, we propose a novel…

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even…

The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been…