A Survey of Adversarial Learning on Graphs

TL;DR

This paper provides a comprehensive survey of adversarial learning on graphs, unifying attack and defense methods, defining key concepts, and summarizing evaluation metrics to guide future research in the field.

Contribution

It offers the first unified problem definition, taxonomy, and evaluation overview of graph adversarial learning, filling a significant gap in existing literature.

Findings

Unified framework for attack and defense in graph learning

Comprehensive taxonomy and definitions for graph adversarial tasks

Summary of evaluation metrics and recent advances

Abstract

Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction, and graph clustering. However, they expose uncertainty and unreliability against the well-designed inputs, i.e., adversarial examples. Accordingly, a line of studies has emerged for both attack and defense addressed in different graph analysis tasks, leading to the arms race in graph adversarial learning. Despite the booming works, there still lacks a unified problem definition and a comprehensive review. To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically. Specifically, we survey and unify the existing works w.r.t. attack and defense in graph analysis tasks, and give appropriate definitions and taxonomies at the same time. Besides, we emphasize the importance of related evaluation metrics, investigate and summarize them comprehensively. Hopefully, our works can provide a comprehensive overview and offer insights for the relevant researchers. Latest advances in graph adversarial learning are summarized in our GitHub repository https://github.com/EdisonLeeeee/Graph-Adversarial-Learning.