paper-with-me

Papers

Understanding the Impact of Graph Reduction on Adversarial Robustness in Graph Neural Networks

2024-12-08 · Kerui Wu, Ka-Ho Chow, Wenqi Wei, Lei Yu

As Graph Neural Networks (GNNs) become increasingly popular for learning from large-scale graph data across various domains, their susceptibility to adversarial attacks when using graph reduction techniques for scalability remains underexplored. In this paper, we present an extensive empirical study to investigate the impact of graph reduction techniques, specifically graph coarsening and sparsification, on the robustness of GNNs against adversarial attacks. Through extensive experiments involving multiple datasets and GNN architectures, we examine the effects of four sparsification and six coarsening methods on the poisoning attacks. Our results indicate that, while graph sparsification can mitigate the effectiveness of certain poisoning attacks, such as Mettack, it has limited impact on others, like PGD. Conversely, graph coarsening tends to amplify the adversarial impact, significantly reducing classification accuracy as the reduction ratio decreases. Additionally, we provide a novel analysis of the causes driving these effects and examine how defensive GNN models perform under graph reduction, offering practical insights for designing robust GNNs within graph acceleration systems.

📄 PDF Abstract BibTeX arXiv:2412.05883

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation

2024-01-28 · Yongyu Wang, Xiaotian Zhuang

Given that no existing graph construction method can generate a perfect graph for a given dataset, graph-based algorithms are often affected by redundant and erroneous edges present within the constructed graphs. In this…

Adversarial AttackAdversarial RobustnessComputational EfficiencyDenoising+1

Transferring Robustness for Graph Neural Network Against Poisoning Attacks

2019-08-20 · Xianfeng Tang, Yandong Li, Yiwei Sun, Huaxiu Yao 외

Graph neural networks (GNNs) are widely used in many applications. However, their robustness against adversarial attacks is criticized. Prior studies show that using unnoticeable modifications on graph topology or nodal …

Graph Neural NetworkNode ClassificationTransfer Learning

Robustifying 3D Perception through Least-Squares Multi-Agent Graphs Object Tracking

2025-07-07 · Maria Damanaki, Ioulia Kapsali, Nikos Piperigkos, Alexandros Gkillas 외

The critical perception capabilities of EdgeAI systems, such as autonomous vehicles, are required to be resilient against adversarial threats, by enabling accurate identification and localization of multiple objects in t…

Autonomous VehiclesObject Tracking

Understanding the Robustness of Graph Neural Networks against Adversarial Attacks

2024-06-20 · Tao Wu, Canyixing Cui, Xingping Xian, Shaojie Qiao 외

Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing …

Adversarial Robustness

Impact of Attention on Adversarial Robustness of Image Classification Models

2021-09-02 · Prachi Agrawal, Narinder Singh Punn, Sanjay Kumar Sonbhadra, Sonali Agarwal

Adversarial attacks against deep learning models have gained significant attention and recent works have proposed explanations for the existence of adversarial examples and techniques to defend the models against these a…

Adversarial RobustnessClassificationimage-classificationImage Classification