arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2101.06855cs.LGcs.CR
收藏

GraphAttacker:一个通用的多任务GraphAttack框架

GraphAttacker: A General Multi-Task GraphAttack Framework

Jinyin Chen, Dunjie Zhang, Zhaoyan Ming, Kejie Huang, Wenrong Jiang, Chen Cui

摘要:

图神经网络(GNN)已经成功地用于许多现实世界应用中的图分析任务。攻击和防御方法之间的竞争也增强了GNN的鲁棒性。本次比赛对抗性训练方法的发展对攻击样例的多样性提出了更高的要求。相比之下,大多数具有特定攻击策略的攻击方法很难满足这样的要求。为了解决这个问题,我们提出了GraphAttacker,一个新的通用图攻击框架,可以灵活地调整结构和攻击策略,根据图分析任务。GraphAttacker通过对三个关键组件进行交替训练来生成对抗性示例:多策略攻击生成器(MAG),相似性搜索器(SD)和攻击搜索器(AD),基于生成对抗网络(GAN)。此外,我们引入了一个新的相似性修改率SMR进行隐形攻击考虑到节点的相似性分布的变化。在各种基准数据集上的实验表明,GraphAttacker在节点分类、图分类和链接预测等图分析任务上,无论是否进行对抗性训练,都能达到最先进的攻击性能。此外,我们还分析了每个任务的独特性及其在统一攻击框架中的具体响应。项目代码可在https://github.com/honoluluuuu/GraphAttacker上获得。

英文摘要:

Graph neural networks (GNNs) have been successfully exploited in graph analysis tasks in many real-world applications. The competition between attack and defense methods also enhances the robustness of GNNs. In this competition, the development of adversarial training methods put forward higher requirement for the diversity of attack examples. By contrast, most attack methods with specific attack strategies are difficult to satisfy such a requirement. To address this problem, we propose GraphAttacker, a novel generic graph attack framework that can flexibly adjust the structures and the attack strategies according to the graph analysis tasks. GraphAttacker generates adversarial examples through alternate training on three key components: the multi-strategy attack generator (MAG), the similarity discriminator (SD), and the attack discriminator (AD), based on the generative adversarial network (GAN). Furthermore, we introduce a novel similarity modification rate SMR to conduct a stealthier attack considering the change of node similarity distribution. Experiments on various benchmark datasets demonstrate that GraphAttacker can achieve state-of-the-art attack performance on graph analysis tasks of node classification, graph classification, and link prediction, no matter the adversarial training is conducted or not. Moreover, we also analyze the unique characteristics of each task and their specific response in the unified attack framework. The project code is available at https://github.com/honoluluuuu/GraphAttacker.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑