相关论文: Exact Certification of (Graph) Neural Networks Aga…

With deep neural networks providing state-of-the-art machine learning models for numerous machine learning tasks, quantifying the robustness of these models has become an important area of research. However, most of the research literature…

This study explores the effectiveness of graph neural networks (GNNs) for vulnerability detection in software code, utilizing a real-world dataset of Java vulnerability-fixing commits. The dataset's structure, based on the number of…

While Graph Neural Networks (GNNs) and Large Language Models (LLMs) are powerful approaches for learning on Text-Attributed Graphs (TAGs), a comprehensive understanding of their robustness remains elusive. Current evaluations are…

Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of class probabilities that vary with the depth of the…

Large Language Models (LLMs) have advanced Graph Neural Networks (GNNs) by enriching node representations with semantic features, giving rise to LLM-enhanced GNNs that achieve notable performance gains. However, the robustness of these…

Output reachability and adversarial robustness are among the most relevant safety properties of neural networks. We show that in the context of Message Passing Neural Networks (MPNN), a common Graph Neural Network (GNN) model, formal…

Neural networks are often susceptible to minor perturbations in input that cause them to misclassify. A recent solution to this problem is the use of globally-robust neural networks, which employ a function to certify that the…

Graph Neural Networks (GNNs) exhibit strong potential in node classification task through a message-passing mechanism. However, their performance often hinges on high-quality node labels, which are challenging to obtain in real-world…

While neural networks have achieved high performance in different learning tasks, their accuracy drops significantly in the presence of small adversarial perturbations to inputs. Defenses based on regularization and adversarial training are…

Link prediction in graph data uses various algorithms and Graph Nerual Network (GNN) models to predict potential relationships between graph nodes. These techniques have found widespread use in numerous real-world applications, including…

Graph Neural Networks (GNNs) have become the standard method for learning from networks across fields ranging from biology to social systems, yet a principled understanding of what enables them to extract meaningful representations, or why…

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true…

Graph Neural Network (GNN) is an emerging technique for graph-based learning tasks such as node classification. In this work, we reveal the vulnerability of GNN to the imbalance of node labels. Traditional solutions for imbalanced…

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in node classification tasks but struggle with label noise in real-world data. Existing studies on graph learning with label noise commonly rely on class-dependent…

Modern machine learning models are sensitive to the manipulation of both the training data (poisoning attacks) and inference data (adversarial examples). Recognizing this issue, the community has developed many empirical defenses against…

We introduce DeepCert, a tool-supported method for verifying the robustness of deep neural network (DNN) image classifiers to contextually relevant perturbations such as blur, haze, and changes in image contrast. While the robustness of DNN…

The graph contrastive learning (GCL) framework has gained remarkable achievements in graph representation learning. However, similar to graph neural networks (GNNs), GCL models are susceptible to graph structural attacks. As an unsupervised…

Graph neural networks (GNNs) have achieved superior performance on node classification tasks in the last few years. Commonly, this is framed in a transductive semi-supervised learning setup wherein the entire graph, including the target…

As Graph Neural Networks (GNNs) become increasingly prevalent in a variety of fields, from social network analysis to protein-protein interaction studies, growing concerns have emerged regarding the unauthorized utilization of personal…

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…