相关论文: Practicable Black-box Evasion Attacks on Link Pred…

In the last years, Deep Learning technology has been proposed in different fields, bringing many advances in each of them, but identifying new threats in these solutions regarding cybersecurity. Those implemented models have brought several…

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…

Lateral Movement (LM) attacks continue to pose a significant threat to enterprise security, enabling adversaries to stealthily compromise critical assets. However, the development and evaluation of LM detection systems are impeded by the…

Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is crucial. However, existing adversarial attack methods, which…

Publishing graph data is widely desired to enable a variety of structural analyses and downstream tasks. However, it also potentially poses severe privacy leakage, as attackers may leverage the released graph data to launch attacks and…

Graph Neural Networks (GNNs) are a class of deep learning models capable of processing graph-structured data, and they have demonstrated significant performance in a variety of real-world applications. Recent studies have found that GNN…

The advancement in wireless communication technologies is becoming more demanding and pervasive. One of the fundamental parameters that limit the efficiency of the network are the security challenges. The communication network is vulnerable…

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…

In network link prediction, it is possible to hide a target link from being predicted with a small perturbation on network structure. This observation may be exploited in many real world scenarios, for example, to preserve privacy, or to…

Deep learning is effective in graph analysis. It is widely applied in many related areas, such as link prediction, node classification, community detection, and graph classification etc. Graph embedding, which learns low-dimensional…

Representing networks as a graph and training a link prediction model using benign connections is an effective method of anomaly-based intrusion detection. Existing works using this technique have shown great success using temporal graph…

Temporal link prediction in dynamic graphs is a fundamental problem in many real-world systems. Existing temporal graph neural networks mainly focus on learning representations of historical interactions. Despite their strong performance,…

Graph embedding has been widely applied in areas such as network analysis, social network mining, recommendation systems, and bioinformatics. However, current graph construction methods often require the prior definition of neighborhood…

It is well-known that deep learning models are vulnerable to small input perturbations. Such perturbed instances are called adversarial examples. Adversarial examples are commonly crafted to fool a model either at training time (poisoning)…

Graph models are widely used to study diffusion processes in contact networks. Recent data-driven research has highlighted the significance of indirect links, where interactions are possible when two nodes visit the same place at different…

Graph Neural Networks (GNNs) have achieved promising results in tasks such as node classification and graph classification. However, recent studies reveal that GNNs are vulnerable to backdoor attacks, posing a significant threat to their…

Graph edge perturbations are dedicated to damaging the prediction of graph neural networks by modifying the graph structure. Previous gray-box attackers employ gradients from the surrogate model to locate the vulnerable edges to perturb the…

In this study, we delve into the robustness of neural network-based LiDAR point cloud tracking models under adversarial attacks, a critical aspect often overlooked in favor of performance enhancement. These models, despite incorporating…

Transferability, the ability of adversarial examples crafted for one model to deceive other models, is crucial for black-box attacks. Despite advancements in attack methods for semantic segmentation, transferability remains limited,…

Serious crime modelling typically needs to be undertaken securely behind a firewall where police knowledge and capabilities can remain undisclosed. Data informing an ongoing incident is often sparse, with a large proportion of relevant data…