Time-aware Gradient Attack on Dynamic Network Link Prediction
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Demystifying Distributed Training of Graph Neural Networks for Link Prediction
Learnable Spatial-Temporal Positional Encoding for Link Prediction
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model Reliability
Efficient Robust Conformal Prediction via Lipschitz-Bounded Networks
Future Link Prediction Without Memory or Aggregation
Understanding Generalization in Node and Link Prediction
토론
이 논문과 연결된 포럼 글이 아직 없습니다.