In network link prediction, it is possible to hide a target link from being predicted with a small perturbation on network structure. This observation may be exploited in many real world scenarios, for example, to preserve privacy, or to exploit financial security. There have been many recent studies to generate adversarial examples to mislead deep learning models on graph data. However, none of the previous work has considered the dynamic nature of real-world systems. In this work, we present the first study of adversarial attack on dynamic network link prediction (DNLP). The proposed attack method, namely time-aware gradient attack (TGA), utilizes the gradient information generated by deep dynamic network embedding (DDNE) across different snapshots to rewire a few links, so as to make DDNE fail to predict target links. We implement TGA in two ways: one is based on traversal search, namely TGA-Tra; and the other is simplified with greedy search for efficiency, namely TGA-Gre. We conduct comprehensive experiments which show the outstanding performance of TGA in attacking DNLP algorithms.
翻译:在网络链接预测中,有可能隐藏一个目标链接,不以网络结构的小扰动来预测目标链接。这种观察可以在许多现实世界情景中加以利用,例如,保护隐私或利用金融安全。最近进行了许多研究,以生成对抗性实例,误导图表数据方面的深层学习模型。然而,以前的工作没有一项考虑到真实世界系统的动态性质。在这项工作中,我们对动态网络链接预测(DNLP)进行了第一次对敌对性攻击的研究。拟议的攻击方法,即时间觉察梯度攻击(TGA),利用不同截图中深动态网络嵌入(DNE)生成的梯度信息,使DNE无法预测目标链接。我们以两种方式实施TGA:一个是建立在跨行搜索上,即TGA-Tra;另一个是用贪婪搜索效率来简化的,即TGA-GE。我们进行全面实验,显示TGA在攻击DNLP算法方面的出色表现。