Time-Aware Gradient Attack on Dynamic Network Link Prediction

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.

Automated summary

In network link prediction, a small perturbation on the network structure can be used to hide a target link from prediction. This can have various applications such as privacy preservation or financial security exploitation. Previous research has focused on generating adversarial examples to mislead deep learning models on graph data, but the dynamic nature of real-world systems has been overlooked. This study presents the first investigation of adversarial attack on dynamic network link prediction (DNLP) and proposes a time-aware gradient attack (TGA) method that utilizes gradient information from deep dynamic network embedding (DDNE) to rewire links and disrupt link prediction.