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.

中文翻译：

---

动态网络链路预测的时间感知梯度攻击

在网络链接预测中，可以通过对网络结构的小扰动来隐藏目标链接，使其不被预测。这种观察可能会在许多现实世界场景中被利用，例如，保护隐私或利用金融安全。最近有许多研究生成对抗性示例来误导图数据的深度学习模型。然而，之前的工作都没有考虑现实世界系统的动态特性。在这项工作中，我们提出了对动态网络链接预测（DNLP）的对抗性攻击的第一项研究。所提出的攻击方法，即时间感知梯度攻击（TGA），利用深度动态网络嵌入（DDNE）在不同快照上生成的梯度信息重新连接一些链接，从而使DDNE无法预测目标链接。我们通过两种方式实现TGA：一种是基于遍历搜索，即TGA-Tra；另一个是通过贪婪搜索效率简化的，即TGA-Gre。我们进行了全面的实验，展示了 TGA 在攻击 DNLP 算法方面的出色性能。