当前位置:
X-MOL 学术
›
arXiv.cs.SI
›
论文详情
Our official English website, www.x-mol.net, welcomes your
feedback! (Note: you will need to create a separate account there.)
Node Copying for Protection Against Graph Neural Network Topology Attacks
arXiv - CS - Social and Information Networks Pub Date : 2020-07-09 , DOI: arxiv-2007.06704 Florence Regol, Soumyasundar Pal and Mark Coates
arXiv - CS - Social and Information Networks Pub Date : 2020-07-09 , DOI: arxiv-2007.06704 Florence Regol, Soumyasundar Pal and Mark Coates
Adversarial attacks can affect the performance of existing deep learning
models. With the increased interest in graph based machine learning techniques,
there have been investigations which suggest that these models are also
vulnerable to attacks. In particular, corruptions of the graph topology can
degrade the performance of graph based learning algorithms severely. This is
due to the fact that the prediction capability of these algorithms relies
mostly on the similarity structure imposed by the graph connectivity.
Therefore, detecting the location of the corruption and correcting the induced
errors becomes crucial. There has been some recent work which tackles the
detection problem, however these methods do not address the effect of the
attack on the downstream learning task. In this work, we propose an algorithm
that uses node copying to mitigate the degradation in classification that is
caused by adversarial attacks. The proposed methodology is applied only after
the model for the downstream task is trained and the added computation cost
scales well for large graphs. Experimental results show the effectiveness of
our approach for several real world datasets.
中文翻译:
节点复制以防止图神经网络拓扑攻击
对抗性攻击会影响现有深度学习模型的性能。随着人们对基于图的机器学习技术越来越感兴趣,有调查表明这些模型也容易受到攻击。特别是,图拓扑的损坏会严重降低基于图的学习算法的性能。这是因为这些算法的预测能力主要依赖于图连通性强加的相似性结构。因此,检测损坏的位置并纠正引起的错误变得至关重要。最近有一些工作解决了检测问题,但是这些方法没有解决攻击对下游学习任务的影响。在这项工作中,我们提出了一种算法,该算法使用节点复制来减轻由对抗性攻击引起的分类退化。只有在训练了下游任务的模型并且增加的计算成本对于大图可以很好地扩展之后,才应用所提出的方法。实验结果表明我们的方法对几个真实世界数据集的有效性。
更新日期:2020-07-15
中文翻译:
节点复制以防止图神经网络拓扑攻击
对抗性攻击会影响现有深度学习模型的性能。随着人们对基于图的机器学习技术越来越感兴趣,有调查表明这些模型也容易受到攻击。特别是,图拓扑的损坏会严重降低基于图的学习算法的性能。这是因为这些算法的预测能力主要依赖于图连通性强加的相似性结构。因此,检测损坏的位置并纠正引起的错误变得至关重要。最近有一些工作解决了检测问题,但是这些方法没有解决攻击对下游学习任务的影响。在这项工作中,我们提出了一种算法,该算法使用节点复制来减轻由对抗性攻击引起的分类退化。只有在训练了下游任务的模型并且增加的计算成本对于大图可以很好地扩展之后,才应用所提出的方法。实验结果表明我们的方法对几个真实世界数据集的有效性。