当前位置: X-MOL 学术arXiv.cs.CR › 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.)
GraphAttacker: A General Multi-Task GraphAttack Framework
arXiv - CS - Cryptography and Security Pub Date : 2021-01-18 , DOI: arxiv-2101.06855
Jinyin Chen, Dunjie Zhang, Zhaoyan Ming, Kejie Huang

Graph Neural Networks (GNNs) have been successfully exploited in graph analysis tasks in many real-world applications. However, GNNs have been shown to have potential security issues imposed by adversarial samples generated by attackers, which achieved great attack performance with almost imperceptible perturbations. What limit the wide application of these attackers are their methods' specificity on a certain graph analysis task, such as node classification or link prediction. We thus propose GraphAttacker, a novel generic graph attack framework that can flexibly adjust the structures and the attack strategies according to the graph analysis tasks. Based on the Generative Adversarial Network (GAN), GraphAttacker generates adversarial samples through alternate training on three key components, the Multi-strategy Attack Generator (MAG), the Similarity Discriminator (SD), and the Attack Discriminator(AD). Furthermore, to achieve attackers within perturbation budget, we propose a novel Similarity Modification Rate (SMR) to quantify the similarity between nodes thus constrain the attack budget. We carry out extensive experiments and the results show that GraphAttacker can achieve state-of-the-art attack performance on graph analysis tasks of node classification, graph classification, and link prediction. Besides, we also analyze the unique characteristics of each task and their specific response in the unified attack framework. We will release GraphAttacker as an open-source simulation platform for future attack researches.

中文翻译:

GraphAttacker:通用的多任务GraphAttack框架

图神经网络(GNN)已成功应用于许多实际应用中的图分析任务中。但是,事实证明,GNN具有潜在的安全性问题,这些问题是由攻击者生成的对抗性样本引起的,这些样本在几乎无法察觉的扰动下实现了出色的攻击性能。限制这些攻击者广泛应用的是他们的方法在某些图分析任务(例如节点分类或链接预测)上的特异性。因此,我们提出了GraphAttacker,这是一种新颖的通用图攻击框架,可以根据图分析任务灵活地调整结构和攻击策略。GraphAttacker基于生成对抗网络(GAN),通过对三个关键组件,多策略攻击生成器(MAG),相似鉴别器(SD)和攻击鉴别器(AD)。此外,为了使攻击者在摄动预算内,我们提出了一种新颖的相似度修改率(SMR)来量化节点之间的相似度,从而限制了攻击预算。我们进行了广泛的实验,结果表明GraphAttacker可以在节点分类,图形分类和链接预测的图形分析任务上实现最新的攻击性能。此外,我们还分析了统一攻击框架中每个任务的独特特征及其特定响应。我们将发布GraphAttacker作为开放源代码仿真平台,供以后进行攻击研究之用。我们提出了一种新颖的相似度修改率(SMR)来量化节点之间的相似度,从而限制了攻击预算。我们进行了广泛的实验,结果表明GraphAttacker可以在节点分类,图形分类和链接预测的图形分析任务上实现最新的攻击性能。此外,我们还分析了统一攻击框架中每个任务的独特特征及其特定响应。我们将发布GraphAttacker作为开放源代码仿真平台,供以后进行攻击研究之用。我们提出了一种新颖的相似度修改率(SMR)来量化节点之间的相似度,从而限制了攻击预算。我们进行了广泛的实验,结果表明GraphAttacker可以在节点分类,图形分类和链接预测的图形分析任务上实现最新的攻击性能。此外,我们还分析了统一攻击框架中每个任务的独特特征及其特定响应。我们将发布GraphAttacker作为开放源代码仿真平台,供以后进行攻击研究之用。和链接预测。此外,我们还分析了统一攻击框架中每个任务的独特特征及其特定响应。我们将发布GraphAttacker作为开放源代码仿真平台,供以后进行攻击研究之用。和链接预测。此外,我们还分析了统一攻击框架中每个任务的独特特征及其特定响应。我们将发布GraphAttacker作为开放源代码仿真平台,供以后进行攻击研究之用。
更新日期:2021-01-19
down
wechat
bug